https://www.aclweb.org/adminwiki/api.php?action=feedcontributions&feedformat=atom&user=JoakimNivreAdmin Wiki - User contributions [en]2026-05-31T23:43:40ZUser contributionsMediaWiki 1.43.6https://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=724272018Q1 Reports: ACL 20182018-03-07T18:18:33Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 60 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 27 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI ===<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
'''Thursday July 19, 2018'''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
''''Friday July 20, 2018''''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}<br />
<br />
== '''Student Research Workshop''' ==<br />
<br />
Student Organisers<br />
* Vered Shwartz, Bar-Ilan University<br />
* Jeniya Tabassum, Ohio State University<br />
* Rob Voigt, Stanford University<br />
<br />
Faculty Advisors to the Student Research Workshop<br />
* Marie-Catherine de Marneffe, Ohio State<br />
* Wanxiang Che, Harbin Institute of Technology<br />
* Malvina Nissim, University of Groningen<br />
<br />
Information about the Student Research Workshop (SRW) for ACL 2018 has been posted at the following URL: https://sites.google.com/view/aclsrw2018/ .<br />
The SRW has applied for a NSF grant of $18,000. The SRW has been awarded $6,000 by Roam analytics and $4,500 by Google. The SRW will be integrated into the main ACL conference during an evening poster session.<br />
Submission deadlines for the SRW are as follows:<br />
* Pre-submission mentoring deadline: February 26, 2018<br />
* Pre-submission mentoring feedback: March 19, 2018<br />
* Paper submission deadline: April 8, 2018<br />
* Review deadline: April 25, 2018<br />
* Acceptance notification: May 2, 2018<br />
* Camera-ready deadline: May 21, 2018<br />
* Travel grant application deadline: (Last date of Early bird registration of Conference)<br />
* Travel grant notification: (Last date of Early bird registration + 5 days)<br />
<br />
The program committee recruitment is complete, with 88 confirmed PC members. Pre-submission and post-acceptance mentors are recruited from the PC members. We have 11 Pre-submission mentors and 11 post-acceptance mentors.<br />
The SRW START site has been set up. The SRW CFP has been distributed to the following lists: ACL member portal, LINGUIST List, MT-list, comp.ai.nat-lang, Corpora, SigIR.<br />
<br />
== '''Conference Handbook Chair''' ==<br />
Jey Han Lau, IBM Research<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
We’ve read Matt Post’s “handbook chair duties” and forked the handbook source code (https://github.com/naacl-org/naacl-handbook). We are currently in discussion with Priscilla and Shiqi to finalise timeline for the handbook creation, which is detailed below. Note that the deadlines are much more compressed than last year, as this time around the deadlines for paper decisions and camera ready is much closer to the conference date. Consequently the PC and workshop organisers will need to start on scheduling before the camera ready deadlines, i.e., soon after acceptance decisions, which can be revised after camera ready (is this feasible?).<br />
<br />
At the moment we are blocking some time off from June 2-8 to work on the handbook, but this may change (depending on the discussion with Priscilla and Shiqi) because NAACL is happening that week and we anticipate that people might be busy (Trevor included). We have started working on the local guide, enlisting help from colleagues who have run conferences here in previous years, and are looking for a cover designer. We will start liaising with PC and workshop chairs soon to clarify some deadlines/expectation, once these dates are confirmed.<br />
<br />
Timeline:<br />
* 27 April: Handbook draft, excluding conference and workshop data<br />
* 25 May: Draft workshop schedules and programs<br />
* 1 June: Final main conference program due (3 weeks for PC to assemble the “order” file)<br />
* 7 June: Final workshop schedules and programs due (10 days for workshop chair to assemble the “order” file)<br />
* 14 June: Final handbook to OmniPress for printing<br />
* 12 July: Handbook arrives in Melbourne<br />
* 15 July: ACL2018 conference starts<br />
<br />
== '''Publicity Chair''' ==<br />
Sarvnaz Karimi, CSIRO<br />
<br />
The publicity effort has so far included disseminating information---including CFPs and other news items such as when the anonymity period started, or when the submission system opened--- on multiple mailing lists. All the announcements are also made on social media (Twitter and Facebook). <br />
<br />
== '''Webmaster and Appmaster''' ==<br />
Andrew MacKinlay, Culture Amp / University of Melbourne<br />
<br />
== '''Local Organising Committee''' ==<br />
Tim Baldwin, University of Melbourne<br><br />
Karin Verspoor, University of Melbourne<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
* '''Sponsorship:''' Local organizers have been receiving sponsorship inquiries and routinely responding with (a) the Sponsorship brochure provided by Priscilla, and (b) the contact information for the ACL sponsorship team. Cecile Paris and Ben Hachey are responsible for Australia-based companies; the PCO will manage the invoices and money for those local sponsorships. The PCO should also be responsible for final collection and display of logos; this is being confirmed. '''To note:''' It is important to maintain a common list of sponsors across domestic and international sponsorships, since some sponsorship opportunities are only available to a single sponsor. (e.g. the domestic organization CSIRO has come on board as the Student Volunteer Sponsor.) This is now happening via a shared Google Spreadsheet.<br />
<br />
* '''Exhibits:''' Nothing specific to report at this stage; depends on final sponsorship numbers and commitments. Space should not be an issue.<br />
<br />
* '''Registration:''' Inquiries related to registration are steadily increasing and it would be good to open registration soon. The PCO is ready with the local hotel blocks (see below) and has estimated that it will take them 1 month to put together the registration form (which will be locally hosted, for tax reasons); now that tutorials and workshops are settled we should be able to open registration. Any reason not to go ahead ASAP? '''Required:''' Final advice on all elements/variations for registration and pricing. (Member vs non-member, Student vs Academic vs Industry, etc.) any other “add-ons” that should be offered at registration.<br />
<br />
* '''Visas:''' General nervousness around Visas; we should provide a webpage with general information about what visa is required and the process for obtaining one.<br />
<br />
* '''Student volunteers:''' Karin will be coordinating the student volunteers, and communication with the Student Research Workshop organizers is underway. The objective is to offer as many students assistance as possible so we would like to avoid overlaps between those obtaining travel grants (which covers registration) and those receiving registration waivers due to volunteering. '''To do:''' set up Expression of Interest form for volunteers and circulate.<br />
<br />
* '''Childcare:''' Trevor is looking after childcare. The PCO has been looking into childcare companies at our request and it is something that can be offered. The conference would need to allocate one of its rooms for childcare, which will most likely mean having to pay for an additional room beyond what we have contracted already (according to the PCO, none of the rooms in the current contract which won’t be used for sessions/workshops/tutorials is suitable for childcare, as this wasn’t part of the original discussion with MCEC). The ratio of carer to child is 1:4 and each carer is around $60 per hour. In addition to the hourly rate, the conference would need to provide a number of materials/resources such as a microwave, fridge, TV (can be obtained from the venue), change mat plus activities such as colouring books and playdoh (activities can be purchased for a few hundred dollars). '''To do:''' Make final decision on how to proceed.<br />
<br />
* Hotel blocks being held (prices in AUD, per night):<br />
<br />
'''5 Star Hotel'''<br />
<br />
* Crown Metropol: Luxe Room with WiFi $295.00<br />
* Pan Pacific: Deluxe King $285.00, Family Queen $285.00<br />
<br />
'''4 Star Hotel'''<br />
<br />
* Crowne Plaza: Standard Room $250.00<br />
* Holiday Inn: Superior Room $230.00<br />
* Quality Hotel Batmans Hill: Economy Room $129.00, Premium Economy $154.00, Premier Room $179.00<br />
<br />
'''3 Star Hotel'''<br />
<br />
* Pensione (all rooms with WiFi): Matchbox (1x single bed) $130.00, Shoebox Double (1x double bed) $150.00, Pensione Double (1x double bed) $160.00<br />
* Ibis Little Bourke Street: Double/Twin Rooms $130.00, Queen Room $140.00<br />
<br />
'''Apartments'''<br />
<br />
* Aria Apartments: One Bedroom Apartments $159.00, Two Bedroom Apartments $259.00, Two Bedroom two bath Apartments $279.00<br />
<br />
== '''Business Office''' ==<br />
Priscilla Rasmussen, ACL<br />
<br />
Since ACL 2018 will be in Melbourne and there would be financial/tax costs if I managed the registration from the ACL Office, it was agreed that the local PCO we have contracted to manage the conference logistics will also manage the registrations. I will be in contact with them to be sure I get the registration statistics we always have and will proof the registration form and act as an advisor on this.<br />
Similarly, I will act as an advisor to the PCO on sponsorships, exhibits, issuing visa invitation letters and overall space and audio visual setup along with the Local Arrangements team who are really quite good and dedicated.<br />
The sponsorships have been slowly coming in. Commitments are only now being made by some of the large and continuing sponsoring companies. And the Local Sponsorship team of Cecile Paris and Ben Hachey are actively reaching out to Australian and New Zealand firms. To date, these are our commitments:<br />
<br />
'''ACL 2018 Sponsorships'''<br />
<br />
{|<br />
! Amount<br />
! Level<br />
! From<br />
|-<br />
| $25,884.00<br />
| Diamond 3-Pack ($47,520) + SRW Student Travel Awards ($4,500)<br>Invoice #2018-1013 2/8/18<br />
| Google<br />
|-<br />
| $3,816.00 <br />
| Silver 3-Pack $8,480<br>Invoice #2018-1011 2/6/18<br />
|Nuance<br />
|-<br />
| $1,560.00 <br />
| Exhibiting 2-Pack (with EMNLP) $3,120<br>Invoice #2018-1012 2/7/18<br />
| Yandex<br />
|-<br />
| $13,960.00 <br />
| Platinum 3-Pack $28,000 + 3-Pack Exhibiting ($4,080)<br>Invoice #2018-1014 2/9/18<br />
| Amazon<br />
|-<br />
| $1,135.75 <br />
| Supporter 2-Pack with EMNLP ($1,925)<br>Invoice #2018-1016 2/12/18<br />
| Matteo Grella<br />
|-<br />
| $15,400.00 <br />
| Platinum level<br>Invoice #2018-1020 2/21/18<br />
| Recruit Institute of Technology<br />
|-<br />
| $13,650.00 <br />
| Platinum 2-Pack with EMNLP ($21,000) + Silver NAACL + 2 Workshops + ACL/EMNLP Exhibiting<br>Invoice #2018-1019 2/20/18<br />
| Facebook<br />
|-<br />
! $75,405.75 <br />
! Total Commitments <br />
!<br />
|}<br />
<br />
'''Main Conference kept in Australia'''<br />
<br />
{|<br />
| $8,800.00 <br />
| Student Volunteers (11,616 AUD)<br />
| CSIRO<br />
|}<br />
<br />
'''SRW'''<br />
<br />
See Google above<br />
<br />
'''Representation Workshop'''<br />
<br />
{|<br />
| $3,000.00 <br />
| Support of the workshop<br />
| Salesforce (Jamie Kiros)<br />
|-<br />
| $1,500.00 <br />
| Support of the workshop<br>check deposited 1/29/18<br />
| Microsoft<br />
|-<br />
| $3,000.00 <br />
| Platinum 2-Pack with EMNLP ($21,000) + Silver NAACL + 2 Workshops<br>Invoice #2018-1019 2/20/18<br />
| Facebook<br />
|-<br />
! $7,500.00 <br />
! Total<br />
!<br />
|}</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=724262018Q1 Reports: ACL 20182018-03-07T18:16:43Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI ===<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
'''Thursday July 19, 2018'''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
''''Friday July 20, 2018''''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}<br />
<br />
== '''Student Research Workshop''' ==<br />
<br />
Student Organisers<br />
* Vered Shwartz, Bar-Ilan University<br />
* Jeniya Tabassum, Ohio State University<br />
* Rob Voigt, Stanford University<br />
<br />
Faculty Advisors to the Student Research Workshop<br />
* Marie-Catherine de Marneffe, Ohio State<br />
* Wanxiang Che, Harbin Institute of Technology<br />
* Malvina Nissim, University of Groningen<br />
<br />
Information about the Student Research Workshop (SRW) for ACL 2018 has been posted at the following URL: https://sites.google.com/view/aclsrw2018/ .<br />
The SRW has applied for a NSF grant of $18,000. The SRW has been awarded $6,000 by Roam analytics and $4,500 by Google. The SRW will be integrated into the main ACL conference during an evening poster session.<br />
Submission deadlines for the SRW are as follows:<br />
* Pre-submission mentoring deadline: February 26, 2018<br />
* Pre-submission mentoring feedback: March 19, 2018<br />
* Paper submission deadline: April 8, 2018<br />
* Review deadline: April 25, 2018<br />
* Acceptance notification: May 2, 2018<br />
* Camera-ready deadline: May 21, 2018<br />
* Travel grant application deadline: (Last date of Early bird registration of Conference)<br />
* Travel grant notification: (Last date of Early bird registration + 5 days)<br />
<br />
The program committee recruitment is complete, with 88 confirmed PC members. Pre-submission and post-acceptance mentors are recruited from the PC members. We have 11 Pre-submission mentors and 11 post-acceptance mentors.<br />
The SRW START site has been set up. The SRW CFP has been distributed to the following lists: ACL member portal, LINGUIST List, MT-list, comp.ai.nat-lang, Corpora, SigIR.<br />
<br />
== '''Conference Handbook Chair''' ==<br />
Jey Han Lau, IBM Research<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
We’ve read Matt Post’s “handbook chair duties” and forked the handbook source code (https://github.com/naacl-org/naacl-handbook). We are currently in discussion with Priscilla and Shiqi to finalise timeline for the handbook creation, which is detailed below. Note that the deadlines are much more compressed than last year, as this time around the deadlines for paper decisions and camera ready is much closer to the conference date. Consequently the PC and workshop organisers will need to start on scheduling before the camera ready deadlines, i.e., soon after acceptance decisions, which can be revised after camera ready (is this feasible?).<br />
<br />
At the moment we are blocking some time off from June 2-8 to work on the handbook, but this may change (depending on the discussion with Priscilla and Shiqi) because NAACL is happening that week and we anticipate that people might be busy (Trevor included). We have started working on the local guide, enlisting help from colleagues who have run conferences here in previous years, and are looking for a cover designer. We will start liaising with PC and workshop chairs soon to clarify some deadlines/expectation, once these dates are confirmed.<br />
<br />
Timeline:<br />
* 27 April: Handbook draft, excluding conference and workshop data<br />
* 25 May: Draft workshop schedules and programs<br />
* 1 June: Final main conference program due (3 weeks for PC to assemble the “order” file)<br />
* 7 June: Final workshop schedules and programs due (10 days for workshop chair to assemble the “order” file)<br />
* 14 June: Final handbook to OmniPress for printing<br />
* 12 July: Handbook arrives in Melbourne<br />
* 15 July: ACL2018 conference starts<br />
<br />
== '''Publicity Chair''' ==<br />
Sarvnaz Karimi, CSIRO<br />
<br />
The publicity effort has so far included disseminating information---including CFPs and other news items such as when the anonymity period started, or when the submission system opened--- on multiple mailing lists. All the announcements are also made on social media (Twitter and Facebook). <br />
<br />
== '''Webmaster and Appmaster''' ==<br />
Andrew MacKinlay, Culture Amp / University of Melbourne<br />
<br />
== '''Local Organising Committee''' ==<br />
Tim Baldwin, University of Melbourne<br><br />
Karin Verspoor, University of Melbourne<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
* '''Sponsorship:''' Local organizers have been receiving sponsorship inquiries and routinely responding with (a) the Sponsorship brochure provided by Priscilla, and (b) the contact information for the ACL sponsorship team. Cecile Paris and Ben Hachey are responsible for Australia-based companies; the PCO will manage the invoices and money for those local sponsorships. The PCO should also be responsible for final collection and display of logos; this is being confirmed. '''To note:''' It is important to maintain a common list of sponsors across domestic and international sponsorships, since some sponsorship opportunities are only available to a single sponsor. (e.g. the domestic organization CSIRO has come on board as the Student Volunteer Sponsor.) This is now happening via a shared Google Spreadsheet.<br />
<br />
* '''Exhibits:''' Nothing specific to report at this stage; depends on final sponsorship numbers and commitments. Space should not be an issue.<br />
<br />
* '''Registration:''' Inquiries related to registration are steadily increasing and it would be good to open registration soon. The PCO is ready with the local hotel blocks (see below) and has estimated that it will take them 1 month to put together the registration form (which will be locally hosted, for tax reasons); now that tutorials and workshops are settled we should be able to open registration. Any reason not to go ahead ASAP? '''Required:''' Final advice on all elements/variations for registration and pricing. (Member vs non-member, Student vs Academic vs Industry, etc.) any other “add-ons” that should be offered at registration.<br />
<br />
* '''Visas:''' General nervousness around Visas; we should provide a webpage with general information about what visa is required and the process for obtaining one.<br />
<br />
* '''Student volunteers:''' Karin will be coordinating the student volunteers, and communication with the Student Research Workshop organizers is underway. The objective is to offer as many students assistance as possible so we would like to avoid overlaps between those obtaining travel grants (which covers registration) and those receiving registration waivers due to volunteering. '''To do:''' set up Expression of Interest form for volunteers and circulate.<br />
<br />
* '''Childcare:''' Trevor is looking after childcare. The PCO has been looking into childcare companies at our request and it is something that can be offered. The conference would need to allocate one of its rooms for childcare, which will most likely mean having to pay for an additional room beyond what we have contracted already (according to the PCO, none of the rooms in the current contract which won’t be used for sessions/workshops/tutorials is suitable for childcare, as this wasn’t part of the original discussion with MCEC). The ratio of carer to child is 1:4 and each carer is around $60 per hour. In addition to the hourly rate, the conference would need to provide a number of materials/resources such as a microwave, fridge, TV (can be obtained from the venue), change mat plus activities such as colouring books and playdoh (activities can be purchased for a few hundred dollars). '''To do:''' Make final decision on how to proceed.<br />
<br />
* Hotel blocks being held (prices in AUD, per night):<br />
<br />
'''5 Star Hotel'''<br />
<br />
* Crown Metropol: Luxe Room with WiFi $295.00<br />
* Pan Pacific: Deluxe King $285.00, Family Queen $285.00<br />
<br />
'''4 Star Hotel'''<br />
<br />
* Crowne Plaza: Standard Room $250.00<br />
* Holiday Inn: Superior Room $230.00<br />
* Quality Hotel Batmans Hill: Economy Room $129.00, Premium Economy $154.00, Premier Room $179.00<br />
<br />
'''3 Star Hotel'''<br />
<br />
* Pensione (all rooms with WiFi): Matchbox (1x single bed) $130.00, Shoebox Double (1x double bed) $150.00, Pensione Double (1x double bed) $160.00<br />
* Ibis Little Bourke Street: Double/Twin Rooms $130.00, Queen Room $140.00<br />
<br />
'''Apartments'''<br />
<br />
* Aria Apartments: One Bedroom Apartments $159.00, Two Bedroom Apartments $259.00, Two Bedroom two bath Apartments $279.00<br />
<br />
== '''Business Office''' ==<br />
Priscilla Rasmussen, ACL<br />
<br />
Since ACL 2018 will be in Melbourne and there would be financial/tax costs if I managed the registration from the ACL Office, it was agreed that the local PCO we have contracted to manage the conference logistics will also manage the registrations. I will be in contact with them to be sure I get the registration statistics we always have and will proof the registration form and act as an advisor on this.<br />
Similarly, I will act as an advisor to the PCO on sponsorships, exhibits, issuing visa invitation letters and overall space and audio visual setup along with the Local Arrangements team who are really quite good and dedicated.<br />
The sponsorships have been slowly coming in. Commitments are only now being made by some of the large and continuing sponsoring companies. And the Local Sponsorship team of Cecile Paris and Ben Hachey are actively reaching out to Australian and New Zealand firms. To date, these are our commitments:<br />
<br />
'''ACL 2018 Sponsorships'''<br />
<br />
{|<br />
! Amount<br />
! Level<br />
! From<br />
|-<br />
| $25,884.00<br />
| Diamond 3-Pack ($47,520) + SRW Student Travel Awards ($4,500)<br>Invoice #2018-1013 2/8/18<br />
| Google<br />
|-<br />
| $3,816.00 <br />
| Silver 3-Pack $8,480<br>Invoice #2018-1011 2/6/18<br />
|Nuance<br />
|-<br />
| $1,560.00 <br />
| Exhibiting 2-Pack (with EMNLP) $3,120<br>Invoice #2018-1012 2/7/18<br />
| Yandex<br />
|-<br />
| $13,960.00 <br />
| Platinum 3-Pack $28,000 + 3-Pack Exhibiting ($4,080)<br>Invoice #2018-1014 2/9/18<br />
| Amazon<br />
|-<br />
| $1,135.75 <br />
| Supporter 2-Pack with EMNLP ($1,925)<br>Invoice #2018-1016 2/12/18<br />
| Matteo Grella<br />
|-<br />
| $15,400.00 <br />
| Platinum level<br>Invoice #2018-1020 2/21/18<br />
| Recruit Institute of Technology<br />
|-<br />
| $13,650.00 <br />
| Platinum 2-Pack with EMNLP ($21,000) + Silver NAACL + 2 Workshops + ACL/EMNLP Exhibiting<br>Invoice #2018-1019 2/20/18<br />
| Facebook<br />
|-<br />
! $75,405.75 <br />
! Total Commitments <br />
!<br />
|}<br />
<br />
'''Main Conference kept in Australia'''<br />
<br />
{|<br />
| $8,800.00 <br />
| Student Volunteers (11,616 AUD)<br />
| CSIRO<br />
|}<br />
<br />
'''SRW'''<br />
<br />
See Google above<br />
<br />
'''Representation Workshop'''<br />
<br />
{|<br />
| $3,000.00 <br />
| Support of the workshop<br />
| Salesforce (Jamie Kiros)<br />
|-<br />
| $1,500.00 <br />
| Support of the workshop<br>check deposited 1/29/18<br />
| Microsoft<br />
|-<br />
| $3,000.00 <br />
| Platinum 2-Pack with EMNLP ($21,000) + Silver NAACL + 2 Workshops<br>Invoice #2018-1019 2/20/18<br />
| Facebook<br />
|-<br />
! $7,500.00 <br />
! Total<br />
!<br />
|}</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=724252018Q1 Reports: ACL 20182018-03-07T18:08:50Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI ===<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
'''Thursday July 19, 2018'''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
''''Friday July 20, 2018''''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}<br />
<br />
== '''Student Research Workshop''' ==<br />
<br />
Student Organisers<br />
* Vered Shwartz, Bar-Ilan University<br />
* Jeniya Tabassum, Ohio State University<br />
* Rob Voigt, Stanford University<br />
<br />
Faculty Advisors to the Student Research Workshop<br />
* Marie-Catherine de Marneffe, Ohio State<br />
* Wanxiang Che, Harbin Institute of Technology<br />
* Malvina Nissim, University of Groningen<br />
<br />
Information about the Student Research Workshop (SRW) for ACL 2018 has been posted at the following URL: https://sites.google.com/view/aclsrw2018/ .<br />
The SRW has applied for a NSF grant of $18,000. The SRW has been awarded $6,000 by Roam analytics and $4,500 by Google. The SRW will be integrated into the main ACL conference during an evening poster session.<br />
Submission deadlines for the SRW are as follows:<br />
* Pre-submission mentoring deadline: February 26, 2018<br />
* Pre-submission mentoring feedback: March 19, 2018<br />
* Paper submission deadline: April 8, 2018<br />
* Review deadline: April 25, 2018<br />
* Acceptance notification: May 2, 2018<br />
* Camera-ready deadline: May 21, 2018<br />
* Travel grant application deadline: (Last date of Early bird registration of Conference)<br />
* Travel grant notification: (Last date of Early bird registration + 5 days)<br />
<br />
The program committee recruitment is complete, with 88 confirmed PC members. Pre-submission and post-acceptance mentors are recruited from the PC members. We have 11 Pre-submission mentors and 11 post-acceptance mentors.<br />
The SRW START site has been set up. The SRW CFP has been distributed to the following lists: ACL member portal, LINGUIST List, MT-list, comp.ai.nat-lang, Corpora, SigIR.<br />
<br />
== '''Conference Handbook Chair''' ==<br />
Jey Han Lau, IBM Research<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
We’ve read Matt Post’s “handbook chair duties” and forked the handbook source code (https://github.com/naacl-org/naacl-handbook). We are currently in discussion with Priscilla and Shiqi to finalise timeline for the handbook creation, which is detailed below. Note that the deadlines are much more compressed than last year, as this time around the deadlines for paper decisions and camera ready is much closer to the conference date. Consequently the PC and workshop organisers will need to start on scheduling before the camera ready deadlines, i.e., soon after acceptance decisions, which can be revised after camera ready (is this feasible?).<br />
<br />
At the moment we are blocking some time off from June 2-8 to work on the handbook, but this may change (depending on the discussion with Priscilla and Shiqi) because NAACL is happening that week and we anticipate that people might be busy (Trevor included). We have started working on the local guide, enlisting help from colleagues who have run conferences here in previous years, and are looking for a cover designer. We will start liaising with PC and workshop chairs soon to clarify some deadlines/expectation, once these dates are confirmed.<br />
<br />
Timeline:<br />
* 27 April: Handbook draft, excluding conference and workshop data<br />
* 25 May: Draft workshop schedules and programs<br />
* 1 June: Final main conference program due (3 weeks for PC to assemble the “order” file)<br />
* 7 June: Final workshop schedules and programs due (10 days for workshop chair to assemble the “order” file)<br />
* 14 June: Final handbook to OmniPress for printing<br />
* 12 July: Handbook arrives in Melbourne<br />
* 15 July: ACL2018 conference starts<br />
<br />
== '''Publicity Chair''' ==<br />
Sarvnaz Karimi, CSIRO<br />
<br />
The publicity effort has so far included disseminating information---including CFPs and other news items such as when the anonymity period started, or when the submission system opened--- on multiple mailing lists. All the announcements are also made on social media (Twitter and Facebook). <br />
<br />
== '''Webmaster and Appmaster''' ==<br />
Andrew MacKinlay, Culture Amp / University of Melbourne<br />
<br />
== '''Local Organising Committee''' ==<br />
Tim Baldwin, University of Melbourne<br><br />
Karin Verspoor, University of Melbourne<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
* '''Sponsorship:''' Local organizers have been receiving sponsorship inquiries and routinely responding with (a) the Sponsorship brochure provided by Priscilla, and (b) the contact information for the ACL sponsorship team. Cecile Paris and Ben Hachey are responsible for Australia-based companies; the PCO will manage the invoices and money for those local sponsorships. The PCO should also be responsible for final collection and display of logos; this is being confirmed. '''To note:''' It is important to maintain a common list of sponsors across domestic and international sponsorships, since some sponsorship opportunities are only available to a single sponsor. (e.g. the domestic organization CSIRO has come on board as the Student Volunteer Sponsor.) This is now happening via a shared Google Spreadsheet.<br />
<br />
* '''Exhibits:''' Nothing specific to report at this stage; depends on final sponsorship numbers and commitments. Space should not be an issue.<br />
<br />
* '''Registration:''' Inquiries related to registration are steadily increasing and it would be good to open registration soon. The PCO is ready with the local hotel blocks (see below) and has estimated that it will take them 1 month to put together the registration form (which will be locally hosted, for tax reasons); now that tutorials and workshops are settled we should be able to open registration. Any reason not to go ahead ASAP? '''Required:''' Final advice on all elements/variations for registration and pricing. (Member vs non-member, Student vs Academic vs Industry, etc.) any other “add-ons” that should be offered at registration.<br />
<br />
* '''Visas:''' General nervousness around Visas; we should provide a webpage with general information about what visa is required and the process for obtaining one.<br />
<br />
* '''Student volunteers:''' Karin will be coordinating the student volunteers, and communication with the Student Research Workshop organizers is underway. The objective is to offer as many students assistance as possible so we would like to avoid overlaps between those obtaining travel grants (which covers registration) and those receiving registration waivers due to volunteering. '''To do:''' set up Expression of Interest form for volunteers and circulate.<br />
<br />
* '''Childcare:''' Trevor is looking after childcare. The PCO has been looking into childcare companies at our request and it is something that can be offered. The conference would need to allocate one of its rooms for childcare, which will most likely mean having to pay for an additional room beyond what we have contracted already (according to the PCO, none of the rooms in the current contract which won’t be used for sessions/workshops/tutorials is suitable for childcare, as this wasn’t part of the original discussion with MCEC). The ratio of carer to child is 1:4 and each carer is around $60 per hour. In addition to the hourly rate, the conference would need to provide a number of materials/resources such as a microwave, fridge, TV (can be obtained from the venue), change mat plus activities such as colouring books and playdoh (activities can be purchased for a few hundred dollars). '''To do:''' Make final decision on how to proceed.<br />
<br />
* Hotel blocks being held (prices in AUD, per night):<br />
<br />
'''5 Star Hotel'''<br />
<br />
* Crown Metropol: Luxe Room with WiFi $295.00<br />
* Pan Pacific: Deluxe King $285.00, Family Queen $285.00<br />
<br />
'''4 Star Hotel'''<br />
<br />
* Crowne Plaza: Standard Room $250.00<br />
* Holiday Inn: Superior Room $230.00<br />
* Quality Hotel Batmans Hill: Economy Room $129.00, Premium Economy $154.00, Premier Room $179.00<br />
<br />
'''3 Star Hotel'''<br />
<br />
* Pensione (all rooms with WiFi): Matchbox (1x single bed) $130.00, Shoebox Double (1x double bed) $150.00, Pensione Double (1x double bed) $160.00<br />
* Ibis Little Bourke Street: Double/Twin Rooms $130.00, Queen Room $140.00<br />
<br />
'''Apartments'''<br />
<br />
* Aria Apartments: One Bedroom Apartments $159.00, Two Bedroom Apartments $259.00, Two Bedroom two bath Apartments $279.00<br />
<br />
== '''Business Office''' ==<br />
Priscilla Rasmussen, ACL<br />
<br />
Since ACL 2018 will be in Melbourne and there would be financial/tax costs if I managed the registration from the ACL Office, it was agreed that the local PCO we have contracted to manage the conference logistics will also manage the registrations. I will be in contact with them to be sure I get the registration statistics we always have and will proof the registration form and act as an advisor on this.<br />
Similarly, I will act as an advisor to the PCO on sponsorships, exhibits, issuing visa invitation letters and overall space and audio visual setup along with the Local Arrangements team who are really quite good and dedicated.<br />
The sponsorships have been slowly coming in. Commitments are only now being made by some of the large and continuing sponsoring companies. And the Local Sponsorship team of Cecile Paris and Ben Hachey are actively reaching out to Australian and New Zealand firms. To date, these are our commitments:<br />
<br />
'''ACL 2018 Sponsorships'''<br />
<br />
{|<br />
! Amount<br />
! Level<br />
! From<br />
|-<br />
| $25,884.00<br />
| Diamond 3-Pack ($47,520) + SRW Student Travel Awards ($4,500), Invoice #2018-1013 2/8/18<br />
| Google<br />
|-<br />
| $3,816.00 <br />
| Silver 3-Pack $8,480<br>Invoice #2018-1011 2/6/18<br />
|Nuance<br />
|-<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
$1,560.00 <br />
Exhibiting 2-Pack (with EMNLP) $3,120<br />
Yandex<br />
<br />
<br />
Invoice #2018-1012 2/7/18<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
$13,960.00 <br />
Platinum 3-Pack $28,000 + 3-Pack Exhibiting ($4,080)<br />
Amazon<br />
<br />
<br />
Invoice #2018-1014 2/9/18<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
$1,135.75 <br />
Supporter 2-Pack with EMNLP ($1,925)<br />
Matteo Grella<br />
<br />
<br />
Invoice #2018-1016 2/12/18<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
$15,400.00 <br />
Platinum level<br />
Recruit Institute of Technology<br />
<br />
<br />
Invoice #2018-1020 2/21/18<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
$13,650.00 <br />
Platinum 2-Pack with EMNLP ($21,000) + Silver NAACL + 2 Workshops + ACL/EMNLP Exhibiting<br />
Facebook<br />
<br />
<br />
Invoice #2018-1019 2/20/18</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=724242018Q1 Reports: ACL 20182018-03-07T18:06:58Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI ===<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
'''Thursday July 19, 2018'''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
''''Friday July 20, 2018''''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}<br />
<br />
== '''Student Research Workshop''' ==<br />
<br />
Student Organisers<br />
* Vered Shwartz, Bar-Ilan University<br />
* Jeniya Tabassum, Ohio State University<br />
* Rob Voigt, Stanford University<br />
<br />
Faculty Advisors to the Student Research Workshop<br />
* Marie-Catherine de Marneffe, Ohio State<br />
* Wanxiang Che, Harbin Institute of Technology<br />
* Malvina Nissim, University of Groningen<br />
<br />
Information about the Student Research Workshop (SRW) for ACL 2018 has been posted at the following URL: https://sites.google.com/view/aclsrw2018/ .<br />
The SRW has applied for a NSF grant of $18,000. The SRW has been awarded $6,000 by Roam analytics and $4,500 by Google. The SRW will be integrated into the main ACL conference during an evening poster session.<br />
Submission deadlines for the SRW are as follows:<br />
* Pre-submission mentoring deadline: February 26, 2018<br />
* Pre-submission mentoring feedback: March 19, 2018<br />
* Paper submission deadline: April 8, 2018<br />
* Review deadline: April 25, 2018<br />
* Acceptance notification: May 2, 2018<br />
* Camera-ready deadline: May 21, 2018<br />
* Travel grant application deadline: (Last date of Early bird registration of Conference)<br />
* Travel grant notification: (Last date of Early bird registration + 5 days)<br />
<br />
The program committee recruitment is complete, with 88 confirmed PC members. Pre-submission and post-acceptance mentors are recruited from the PC members. We have 11 Pre-submission mentors and 11 post-acceptance mentors.<br />
The SRW START site has been set up. The SRW CFP has been distributed to the following lists: ACL member portal, LINGUIST List, MT-list, comp.ai.nat-lang, Corpora, SigIR.<br />
<br />
== '''Conference Handbook Chair''' ==<br />
Jey Han Lau, IBM Research<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
We’ve read Matt Post’s “handbook chair duties” and forked the handbook source code (https://github.com/naacl-org/naacl-handbook). We are currently in discussion with Priscilla and Shiqi to finalise timeline for the handbook creation, which is detailed below. Note that the deadlines are much more compressed than last year, as this time around the deadlines for paper decisions and camera ready is much closer to the conference date. Consequently the PC and workshop organisers will need to start on scheduling before the camera ready deadlines, i.e., soon after acceptance decisions, which can be revised after camera ready (is this feasible?).<br />
<br />
At the moment we are blocking some time off from June 2-8 to work on the handbook, but this may change (depending on the discussion with Priscilla and Shiqi) because NAACL is happening that week and we anticipate that people might be busy (Trevor included). We have started working on the local guide, enlisting help from colleagues who have run conferences here in previous years, and are looking for a cover designer. We will start liaising with PC and workshop chairs soon to clarify some deadlines/expectation, once these dates are confirmed.<br />
<br />
Timeline:<br />
* 27 April: Handbook draft, excluding conference and workshop data<br />
* 25 May: Draft workshop schedules and programs<br />
* 1 June: Final main conference program due (3 weeks for PC to assemble the “order” file)<br />
* 7 June: Final workshop schedules and programs due (10 days for workshop chair to assemble the “order” file)<br />
* 14 June: Final handbook to OmniPress for printing<br />
* 12 July: Handbook arrives in Melbourne<br />
* 15 July: ACL2018 conference starts<br />
<br />
== '''Publicity Chair''' ==<br />
Sarvnaz Karimi, CSIRO<br />
<br />
The publicity effort has so far included disseminating information---including CFPs and other news items such as when the anonymity period started, or when the submission system opened--- on multiple mailing lists. All the announcements are also made on social media (Twitter and Facebook). <br />
<br />
== '''Webmaster and Appmaster''' ==<br />
Andrew MacKinlay, Culture Amp / University of Melbourne<br />
<br />
== '''Local Organising Committee''' ==<br />
Tim Baldwin, University of Melbourne<br><br />
Karin Verspoor, University of Melbourne<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
* '''Sponsorship:''' Local organizers have been receiving sponsorship inquiries and routinely responding with (a) the Sponsorship brochure provided by Priscilla, and (b) the contact information for the ACL sponsorship team. Cecile Paris and Ben Hachey are responsible for Australia-based companies; the PCO will manage the invoices and money for those local sponsorships. The PCO should also be responsible for final collection and display of logos; this is being confirmed. '''To note:''' It is important to maintain a common list of sponsors across domestic and international sponsorships, since some sponsorship opportunities are only available to a single sponsor. (e.g. the domestic organization CSIRO has come on board as the Student Volunteer Sponsor.) This is now happening via a shared Google Spreadsheet.<br />
<br />
* '''Exhibits:''' Nothing specific to report at this stage; depends on final sponsorship numbers and commitments. Space should not be an issue.<br />
<br />
* '''Registration:''' Inquiries related to registration are steadily increasing and it would be good to open registration soon. The PCO is ready with the local hotel blocks (see below) and has estimated that it will take them 1 month to put together the registration form (which will be locally hosted, for tax reasons); now that tutorials and workshops are settled we should be able to open registration. Any reason not to go ahead ASAP? '''Required:''' Final advice on all elements/variations for registration and pricing. (Member vs non-member, Student vs Academic vs Industry, etc.) any other “add-ons” that should be offered at registration.<br />
<br />
* '''Visas:''' General nervousness around Visas; we should provide a webpage with general information about what visa is required and the process for obtaining one.<br />
<br />
* '''Student volunteers:''' Karin will be coordinating the student volunteers, and communication with the Student Research Workshop organizers is underway. The objective is to offer as many students assistance as possible so we would like to avoid overlaps between those obtaining travel grants (which covers registration) and those receiving registration waivers due to volunteering. '''To do:''' set up Expression of Interest form for volunteers and circulate.<br />
<br />
* '''Childcare:''' Trevor is looking after childcare. The PCO has been looking into childcare companies at our request and it is something that can be offered. The conference would need to allocate one of its rooms for childcare, which will most likely mean having to pay for an additional room beyond what we have contracted already (according to the PCO, none of the rooms in the current contract which won’t be used for sessions/workshops/tutorials is suitable for childcare, as this wasn’t part of the original discussion with MCEC). The ratio of carer to child is 1:4 and each carer is around $60 per hour. In addition to the hourly rate, the conference would need to provide a number of materials/resources such as a microwave, fridge, TV (can be obtained from the venue), change mat plus activities such as colouring books and playdoh (activities can be purchased for a few hundred dollars). '''To do:''' Make final decision on how to proceed.<br />
<br />
* Hotel blocks being held (prices in AUD, per night):<br />
<br />
'''5 Star Hotel'''<br />
<br />
* Crown Metropol: Luxe Room with WiFi $295.00<br />
* Pan Pacific: Deluxe King $285.00, Family Queen $285.00<br />
<br />
'''4 Star Hotel'''<br />
<br />
* Crowne Plaza: Standard Room $250.00<br />
* Holiday Inn: Superior Room $230.00<br />
* Quality Hotel Batmans Hill: Economy Room $129.00, Premium Economy $154.00, Premier Room $179.00<br />
<br />
'''3 Star Hotel'''<br />
<br />
* Pensione (all rooms with WiFi): Matchbox (1x single bed) $130.00, Shoebox Double (1x double bed) $150.00, Pensione Double (1x double bed) $160.00<br />
* Ibis Little Bourke Street: Double/Twin Rooms $130.00, Queen Room $140.00<br />
<br />
'''Apartments'''<br />
<br />
* Aria Apartments: One Bedroom Apartments $159.00, Two Bedroom Apartments $259.00, Two Bedroom two bath Apartments $279.00<br />
<br />
== '''Business Office''' ==<br />
Priscilla Rasmussen, ACL<br />
<br />
Since ACL 2018 will be in Melbourne and there would be financial/tax costs if I managed the registration from the ACL Office, it was agreed that the local PCO we have contracted to manage the conference logistics will also manage the registrations. I will be in contact with them to be sure I get the registration statistics we always have and will proof the registration form and act as an advisor on this.<br />
Similarly, I will act as an advisor to the PCO on sponsorships, exhibits, issuing visa invitation letters and overall space and audio visual setup along with the Local Arrangements team who are really quite good and dedicated.<br />
The sponsorships have been slowly coming in. Commitments are only now being made by some of the large and continuing sponsoring companies. And the Local Sponsorship team of Cecile Paris and Ben Hachey are actively reaching out to Australian and New Zealand firms. To date, these are our commitments:<br />
<br />
'''ACL 2018 Sponsorships'''<br />
<br />
{|<br />
! Amount<br />
! Level<br />
! From<br />
|-<br />
| $25,884.00<br />
| Diamond 3-Pack ($47,520) + SRW Student Travel Awards ($4,500)<br />
| Google<br />
|<br />
| Invoice #2018-1013 2/8/18<br />
|<br />
|-} <br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
$3,816.00 <br />
Silver 3-Pack $8,480<br />
Nuance<br />
<br />
<br />
Invoice #2018-1011 2/6/18<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
$1,560.00 <br />
Exhibiting 2-Pack (with EMNLP) $3,120<br />
Yandex<br />
<br />
<br />
Invoice #2018-1012 2/7/18<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
$13,960.00 <br />
Platinum 3-Pack $28,000 + 3-Pack Exhibiting ($4,080)<br />
Amazon<br />
<br />
<br />
Invoice #2018-1014 2/9/18<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
$1,135.75 <br />
Supporter 2-Pack with EMNLP ($1,925)<br />
Matteo Grella<br />
<br />
<br />
Invoice #2018-1016 2/12/18<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
$15,400.00 <br />
Platinum level<br />
Recruit Institute of Technology<br />
<br />
<br />
Invoice #2018-1020 2/21/18<br />
<br />
<br />
<br />
<br />
<br />
<br />
<br />
$13,650.00 <br />
Platinum 2-Pack with EMNLP ($21,000) + Silver NAACL + 2 Workshops + ACL/EMNLP Exhibiting<br />
Facebook<br />
<br />
<br />
Invoice #2018-1019 2/20/18</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=724232018Q1 Reports: ACL 20182018-03-07T18:03:08Z<p>JoakimNivre: /* Business Office */</p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI ===<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
'''Thursday July 19, 2018'''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
''''Friday July 20, 2018''''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}<br />
<br />
== '''Student Research Workshop''' ==<br />
<br />
Student Organisers<br />
* Vered Shwartz, Bar-Ilan University<br />
* Jeniya Tabassum, Ohio State University<br />
* Rob Voigt, Stanford University<br />
<br />
Faculty Advisors to the Student Research Workshop<br />
* Marie-Catherine de Marneffe, Ohio State<br />
* Wanxiang Che, Harbin Institute of Technology<br />
* Malvina Nissim, University of Groningen<br />
<br />
Information about the Student Research Workshop (SRW) for ACL 2018 has been posted at the following URL: https://sites.google.com/view/aclsrw2018/ .<br />
The SRW has applied for a NSF grant of $18,000. The SRW has been awarded $6,000 by Roam analytics and $4,500 by Google. The SRW will be integrated into the main ACL conference during an evening poster session.<br />
Submission deadlines for the SRW are as follows:<br />
* Pre-submission mentoring deadline: February 26, 2018<br />
* Pre-submission mentoring feedback: March 19, 2018<br />
* Paper submission deadline: April 8, 2018<br />
* Review deadline: April 25, 2018<br />
* Acceptance notification: May 2, 2018<br />
* Camera-ready deadline: May 21, 2018<br />
* Travel grant application deadline: (Last date of Early bird registration of Conference)<br />
* Travel grant notification: (Last date of Early bird registration + 5 days)<br />
<br />
The program committee recruitment is complete, with 88 confirmed PC members. Pre-submission and post-acceptance mentors are recruited from the PC members. We have 11 Pre-submission mentors and 11 post-acceptance mentors.<br />
The SRW START site has been set up. The SRW CFP has been distributed to the following lists: ACL member portal, LINGUIST List, MT-list, comp.ai.nat-lang, Corpora, SigIR.<br />
<br />
== '''Conference Handbook Chair''' ==<br />
Jey Han Lau, IBM Research<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
We’ve read Matt Post’s “handbook chair duties” and forked the handbook source code (https://github.com/naacl-org/naacl-handbook). We are currently in discussion with Priscilla and Shiqi to finalise timeline for the handbook creation, which is detailed below. Note that the deadlines are much more compressed than last year, as this time around the deadlines for paper decisions and camera ready is much closer to the conference date. Consequently the PC and workshop organisers will need to start on scheduling before the camera ready deadlines, i.e., soon after acceptance decisions, which can be revised after camera ready (is this feasible?).<br />
<br />
At the moment we are blocking some time off from June 2-8 to work on the handbook, but this may change (depending on the discussion with Priscilla and Shiqi) because NAACL is happening that week and we anticipate that people might be busy (Trevor included). We have started working on the local guide, enlisting help from colleagues who have run conferences here in previous years, and are looking for a cover designer. We will start liaising with PC and workshop chairs soon to clarify some deadlines/expectation, once these dates are confirmed.<br />
<br />
Timeline:<br />
* 27 April: Handbook draft, excluding conference and workshop data<br />
* 25 May: Draft workshop schedules and programs<br />
* 1 June: Final main conference program due (3 weeks for PC to assemble the “order” file)<br />
* 7 June: Final workshop schedules and programs due (10 days for workshop chair to assemble the “order” file)<br />
* 14 June: Final handbook to OmniPress for printing<br />
* 12 July: Handbook arrives in Melbourne<br />
* 15 July: ACL2018 conference starts<br />
<br />
== '''Publicity Chair''' ==<br />
Sarvnaz Karimi, CSIRO<br />
<br />
The publicity effort has so far included disseminating information---including CFPs and other news items such as when the anonymity period started, or when the submission system opened--- on multiple mailing lists. All the announcements are also made on social media (Twitter and Facebook). <br />
<br />
== '''Webmaster and Appmaster''' ==<br />
Andrew MacKinlay, Culture Amp / University of Melbourne<br />
<br />
== '''Local Organising Committee''' ==<br />
Tim Baldwin, University of Melbourne<br><br />
Karin Verspoor, University of Melbourne<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
* '''Sponsorship:''' Local organizers have been receiving sponsorship inquiries and routinely responding with (a) the Sponsorship brochure provided by Priscilla, and (b) the contact information for the ACL sponsorship team. Cecile Paris and Ben Hachey are responsible for Australia-based companies; the PCO will manage the invoices and money for those local sponsorships. The PCO should also be responsible for final collection and display of logos; this is being confirmed. '''To note:''' It is important to maintain a common list of sponsors across domestic and international sponsorships, since some sponsorship opportunities are only available to a single sponsor. (e.g. the domestic organization CSIRO has come on board as the Student Volunteer Sponsor.) This is now happening via a shared Google Spreadsheet.<br />
<br />
* '''Exhibits:''' Nothing specific to report at this stage; depends on final sponsorship numbers and commitments. Space should not be an issue.<br />
<br />
* '''Registration:''' Inquiries related to registration are steadily increasing and it would be good to open registration soon. The PCO is ready with the local hotel blocks (see below) and has estimated that it will take them 1 month to put together the registration form (which will be locally hosted, for tax reasons); now that tutorials and workshops are settled we should be able to open registration. Any reason not to go ahead ASAP? '''Required:''' Final advice on all elements/variations for registration and pricing. (Member vs non-member, Student vs Academic vs Industry, etc.) any other “add-ons” that should be offered at registration.<br />
<br />
* '''Visas:''' General nervousness around Visas; we should provide a webpage with general information about what visa is required and the process for obtaining one.<br />
<br />
* '''Student volunteers:''' Karin will be coordinating the student volunteers, and communication with the Student Research Workshop organizers is underway. The objective is to offer as many students assistance as possible so we would like to avoid overlaps between those obtaining travel grants (which covers registration) and those receiving registration waivers due to volunteering. '''To do:''' set up Expression of Interest form for volunteers and circulate.<br />
<br />
* '''Childcare:''' Trevor is looking after childcare. The PCO has been looking into childcare companies at our request and it is something that can be offered. The conference would need to allocate one of its rooms for childcare, which will most likely mean having to pay for an additional room beyond what we have contracted already (according to the PCO, none of the rooms in the current contract which won’t be used for sessions/workshops/tutorials is suitable for childcare, as this wasn’t part of the original discussion with MCEC). The ratio of carer to child is 1:4 and each carer is around $60 per hour. In addition to the hourly rate, the conference would need to provide a number of materials/resources such as a microwave, fridge, TV (can be obtained from the venue), change mat plus activities such as colouring books and playdoh (activities can be purchased for a few hundred dollars). '''To do:''' Make final decision on how to proceed.<br />
<br />
* Hotel blocks being held (prices in AUD, per night):<br />
<br />
'''5 Star Hotel'''<br />
<br />
* Crown Metropol: Luxe Room with WiFi $295.00<br />
* Pan Pacific: Deluxe King $285.00, Family Queen $285.00<br />
<br />
'''4 Star Hotel'''<br />
<br />
* Crowne Plaza: Standard Room $250.00<br />
* Holiday Inn: Superior Room $230.00<br />
* Quality Hotel Batmans Hill: Economy Room $129.00, Premium Economy $154.00, Premier Room $179.00<br />
<br />
'''3 Star Hotel'''<br />
<br />
* Pensione (all rooms with WiFi): Matchbox (1x single bed) $130.00, Shoebox Double (1x double bed) $150.00, Pensione Double (1x double bed) $160.00<br />
* Ibis Little Bourke Street: Double/Twin Rooms $130.00, Queen Room $140.00<br />
<br />
'''Apartments'''<br />
<br />
* Aria Apartments: One Bedroom Apartments $159.00, Two Bedroom Apartments $259.00, Two Bedroom two bath Apartments $279.00<br />
<br />
== '''Business Office''' ==<br />
Priscilla Rasmussen, ACL<br />
<br />
Since ACL 2018 will be in Melbourne and there would be financial/tax costs if I managed the registration from the ACL Office, it was agreed that the local PCO we have contracted to manage the conference logistics will also manage the registrations. I will be in contact with them to be sure I get the registration statistics we always have and will proof the registration form and act as an advisor on this.<br />
Similarly, I will act as an advisor to the PCO on sponsorships, exhibits, issuing visa invitation letters and overall space and audio visual setup along with the Local Arrangements team who are really quite good and dedicated.<br />
The sponsorships have been slowly coming in. Commitments are only now being made by some of the large and continuing sponsoring companies. And the Local Sponsorship team of Cecile Paris and Ben Hachey are actively reaching out to Australian and New Zealand firms. To date, these are our commitments:</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=724012018Q1 Reports: ACL 20182018-03-04T15:40:34Z<p>JoakimNivre: /* Local Organising Committee */</p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI ===<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
'''Thursday July 19, 2018'''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
''''Friday July 20, 2018''''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}<br />
<br />
== '''Student Research Workshop''' ==<br />
<br />
Student Organisers<br />
* Vered Shwartz, Bar-Ilan University<br />
* Jeniya Tabassum, Ohio State University<br />
* Rob Voigt, Stanford University<br />
<br />
Faculty Advisors to the Student Research Workshop<br />
* Marie-Catherine de Marneffe, Ohio State<br />
* Wanxiang Che, Harbin Institute of Technology<br />
* Malvina Nissim, University of Groningen<br />
<br />
Information about the Student Research Workshop (SRW) for ACL 2018 has been posted at the following URL: https://sites.google.com/view/aclsrw2018/ .<br />
The SRW has applied for a NSF grant of $18,000. The SRW has been awarded $6,000 by Roam analytics and $4,500 by Google. The SRW will be integrated into the main ACL conference during an evening poster session.<br />
Submission deadlines for the SRW are as follows:<br />
* Pre-submission mentoring deadline: February 26, 2018<br />
* Pre-submission mentoring feedback: March 19, 2018<br />
* Paper submission deadline: April 8, 2018<br />
* Review deadline: April 25, 2018<br />
* Acceptance notification: May 2, 2018<br />
* Camera-ready deadline: May 21, 2018<br />
* Travel grant application deadline: (Last date of Early bird registration of Conference)<br />
* Travel grant notification: (Last date of Early bird registration + 5 days)<br />
<br />
The program committee recruitment is complete, with 88 confirmed PC members. Pre-submission and post-acceptance mentors are recruited from the PC members. We have 11 Pre-submission mentors and 11 post-acceptance mentors.<br />
The SRW START site has been set up. The SRW CFP has been distributed to the following lists: ACL member portal, LINGUIST List, MT-list, comp.ai.nat-lang, Corpora, SigIR.<br />
<br />
== '''Conference Handbook Chair''' ==<br />
Jey Han Lau, IBM Research<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
We’ve read Matt Post’s “handbook chair duties” and forked the handbook source code (https://github.com/naacl-org/naacl-handbook). We are currently in discussion with Priscilla and Shiqi to finalise timeline for the handbook creation, which is detailed below. Note that the deadlines are much more compressed than last year, as this time around the deadlines for paper decisions and camera ready is much closer to the conference date. Consequently the PC and workshop organisers will need to start on scheduling before the camera ready deadlines, i.e., soon after acceptance decisions, which can be revised after camera ready (is this feasible?).<br />
<br />
At the moment we are blocking some time off from June 2-8 to work on the handbook, but this may change (depending on the discussion with Priscilla and Shiqi) because NAACL is happening that week and we anticipate that people might be busy (Trevor included). We have started working on the local guide, enlisting help from colleagues who have run conferences here in previous years, and are looking for a cover designer. We will start liaising with PC and workshop chairs soon to clarify some deadlines/expectation, once these dates are confirmed.<br />
<br />
Timeline:<br />
* 27 April: Handbook draft, excluding conference and workshop data<br />
* 25 May: Draft workshop schedules and programs<br />
* 1 June: Final main conference program due (3 weeks for PC to assemble the “order” file)<br />
* 7 June: Final workshop schedules and programs due (10 days for workshop chair to assemble the “order” file)<br />
* 14 June: Final handbook to OmniPress for printing<br />
* 12 July: Handbook arrives in Melbourne<br />
* 15 July: ACL2018 conference starts<br />
<br />
== '''Publicity Chair''' ==<br />
Sarvnaz Karimi, CSIRO<br />
<br />
The publicity effort has so far included disseminating information---including CFPs and other news items such as when the anonymity period started, or when the submission system opened--- on multiple mailing lists. All the announcements are also made on social media (Twitter and Facebook). <br />
<br />
== '''Webmaster and Appmaster''' ==<br />
Andrew MacKinlay, Culture Amp / University of Melbourne<br />
<br />
== '''Local Organising Committee''' ==<br />
Tim Baldwin, University of Melbourne<br><br />
Karin Verspoor, University of Melbourne<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
* '''Sponsorship:''' Local organizers have been receiving sponsorship inquiries and routinely responding with (a) the Sponsorship brochure provided by Priscilla, and (b) the contact information for the ACL sponsorship team. Cecile Paris and Ben Hachey are responsible for Australia-based companies; the PCO will manage the invoices and money for those local sponsorships. The PCO should also be responsible for final collection and display of logos; this is being confirmed. '''To note:''' It is important to maintain a common list of sponsors across domestic and international sponsorships, since some sponsorship opportunities are only available to a single sponsor. (e.g. the domestic organization CSIRO has come on board as the Student Volunteer Sponsor.) This is now happening via a shared Google Spreadsheet.<br />
<br />
* '''Exhibits:''' Nothing specific to report at this stage; depends on final sponsorship numbers and commitments. Space should not be an issue.<br />
<br />
* '''Registration:''' Inquiries related to registration are steadily increasing and it would be good to open registration soon. The PCO is ready with the local hotel blocks (see below) and has estimated that it will take them 1 month to put together the registration form (which will be locally hosted, for tax reasons); now that tutorials and workshops are settled we should be able to open registration. Any reason not to go ahead ASAP? '''Required:''' Final advice on all elements/variations for registration and pricing. (Member vs non-member, Student vs Academic vs Industry, etc.) any other “add-ons” that should be offered at registration.<br />
<br />
* '''Visas:''' General nervousness around Visas; we should provide a webpage with general information about what visa is required and the process for obtaining one.<br />
<br />
* '''Student volunteers:''' Karin will be coordinating the student volunteers, and communication with the Student Research Workshop organizers is underway. The objective is to offer as many students assistance as possible so we would like to avoid overlaps between those obtaining travel grants (which covers registration) and those receiving registration waivers due to volunteering. '''To do:''' set up Expression of Interest form for volunteers and circulate.<br />
<br />
* '''Childcare:''' Trevor is looking after childcare. The PCO has been looking into childcare companies at our request and it is something that can be offered. The conference would need to allocate one of its rooms for childcare, which will most likely mean having to pay for an additional room beyond what we have contracted already (according to the PCO, none of the rooms in the current contract which won’t be used for sessions/workshops/tutorials is suitable for childcare, as this wasn’t part of the original discussion with MCEC). The ratio of carer to child is 1:4 and each carer is around $60 per hour. In addition to the hourly rate, the conference would need to provide a number of materials/resources such as a microwave, fridge, TV (can be obtained from the venue), change mat plus activities such as colouring books and playdoh (activities can be purchased for a few hundred dollars). '''To do:''' Make final decision on how to proceed.<br />
<br />
* Hotel blocks being held (prices in AUD, per night):<br />
<br />
'''5 Star Hotel'''<br />
<br />
* Crown Metropol: Luxe Room with WiFi $295.00<br />
* Pan Pacific: Deluxe King $285.00, Family Queen $285.00<br />
<br />
'''4 Star Hotel'''<br />
<br />
* Crowne Plaza: Standard Room $250.00<br />
* Holiday Inn: Superior Room $230.00<br />
* Quality Hotel Batmans Hill: Economy Room $129.00, Premium Economy $154.00, Premier Room $179.00<br />
<br />
'''3 Star Hotel'''<br />
<br />
* Pensione (all rooms with WiFi): Matchbox (1x single bed) $130.00, Shoebox Double (1x double bed) $150.00, Pensione Double (1x double bed) $160.00<br />
* Ibis Little Bourke Street: Double/Twin Rooms $130.00, Queen Room $140.00<br />
<br />
'''Apartments'''<br />
<br />
* Aria Apartments: One Bedroom Apartments $159.00, Two Bedroom Apartments $259.00, Two Bedroom two bath Apartments $279.00<br />
<br />
== '''Business Office''' ==<br />
Priscilla Rasmussen, ACL</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=724002018Q1 Reports: ACL 20182018-03-04T15:34:36Z<p>JoakimNivre: /* Local Organising Committee */</p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI ===<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
'''Thursday July 19, 2018'''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
''''Friday July 20, 2018''''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}<br />
<br />
== '''Student Research Workshop''' ==<br />
<br />
Student Organisers<br />
* Vered Shwartz, Bar-Ilan University<br />
* Jeniya Tabassum, Ohio State University<br />
* Rob Voigt, Stanford University<br />
<br />
Faculty Advisors to the Student Research Workshop<br />
* Marie-Catherine de Marneffe, Ohio State<br />
* Wanxiang Che, Harbin Institute of Technology<br />
* Malvina Nissim, University of Groningen<br />
<br />
Information about the Student Research Workshop (SRW) for ACL 2018 has been posted at the following URL: https://sites.google.com/view/aclsrw2018/ .<br />
The SRW has applied for a NSF grant of $18,000. The SRW has been awarded $6,000 by Roam analytics and $4,500 by Google. The SRW will be integrated into the main ACL conference during an evening poster session.<br />
Submission deadlines for the SRW are as follows:<br />
* Pre-submission mentoring deadline: February 26, 2018<br />
* Pre-submission mentoring feedback: March 19, 2018<br />
* Paper submission deadline: April 8, 2018<br />
* Review deadline: April 25, 2018<br />
* Acceptance notification: May 2, 2018<br />
* Camera-ready deadline: May 21, 2018<br />
* Travel grant application deadline: (Last date of Early bird registration of Conference)<br />
* Travel grant notification: (Last date of Early bird registration + 5 days)<br />
<br />
The program committee recruitment is complete, with 88 confirmed PC members. Pre-submission and post-acceptance mentors are recruited from the PC members. We have 11 Pre-submission mentors and 11 post-acceptance mentors.<br />
The SRW START site has been set up. The SRW CFP has been distributed to the following lists: ACL member portal, LINGUIST List, MT-list, comp.ai.nat-lang, Corpora, SigIR.<br />
<br />
== '''Conference Handbook Chair''' ==<br />
Jey Han Lau, IBM Research<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
We’ve read Matt Post’s “handbook chair duties” and forked the handbook source code (https://github.com/naacl-org/naacl-handbook). We are currently in discussion with Priscilla and Shiqi to finalise timeline for the handbook creation, which is detailed below. Note that the deadlines are much more compressed than last year, as this time around the deadlines for paper decisions and camera ready is much closer to the conference date. Consequently the PC and workshop organisers will need to start on scheduling before the camera ready deadlines, i.e., soon after acceptance decisions, which can be revised after camera ready (is this feasible?).<br />
<br />
At the moment we are blocking some time off from June 2-8 to work on the handbook, but this may change (depending on the discussion with Priscilla and Shiqi) because NAACL is happening that week and we anticipate that people might be busy (Trevor included). We have started working on the local guide, enlisting help from colleagues who have run conferences here in previous years, and are looking for a cover designer. We will start liaising with PC and workshop chairs soon to clarify some deadlines/expectation, once these dates are confirmed.<br />
<br />
Timeline:<br />
* 27 April: Handbook draft, excluding conference and workshop data<br />
* 25 May: Draft workshop schedules and programs<br />
* 1 June: Final main conference program due (3 weeks for PC to assemble the “order” file)<br />
* 7 June: Final workshop schedules and programs due (10 days for workshop chair to assemble the “order” file)<br />
* 14 June: Final handbook to OmniPress for printing<br />
* 12 July: Handbook arrives in Melbourne<br />
* 15 July: ACL2018 conference starts<br />
<br />
== '''Publicity Chair''' ==<br />
Sarvnaz Karimi, CSIRO<br />
<br />
The publicity effort has so far included disseminating information---including CFPs and other news items such as when the anonymity period started, or when the submission system opened--- on multiple mailing lists. All the announcements are also made on social media (Twitter and Facebook). <br />
<br />
== '''Webmaster and Appmaster''' ==<br />
Andrew MacKinlay, Culture Amp / University of Melbourne<br />
<br />
== '''Local Organising Committee''' ==<br />
Tim Baldwin, University of Melbourne<br><br />
Karin Verspoor, University of Melbourne<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
* '''Sponsorship:''' Local organizers have been receiving sponsorship inquiries and routinely responding with (a) the Sponsorship brochure provided by Priscilla, and (b) the contact information for the ACL sponsorship team. Cecile Paris and Ben Hachey are responsible for Australia-based companies; the PCO will manage the invoices and money for those local sponsorships. The PCO should also be responsible for final collection and display of logos; this is being confirmed. '''To note:''' It is important to maintain a common list of sponsors across domestic and international sponsorships, since some sponsorship opportunities are only available to a single sponsor. (e.g. the domestic organization CSIRO has come on board as the Student Volunteer Sponsor.) This is now happening via a shared Google Spreadsheet.<br />
<br />
* '''Exhibits:''' Nothing specific to report at this stage; depends on final sponsorship numbers and commitments. Space should not be an issue.<br />
<br />
* '''Registration:''' Inquiries related to registration are steadily increasing and it would be good to open registration soon. The PCO is ready with the local hotel blocks (see below) and has estimated that it will take them 1 month to put together the registration form (which will be locally hosted, for tax reasons); now that tutorials and workshops are settled we should be able to open registration. Any reason not to go ahead ASAP? '''Required:''' Final advice on all elements/variations for registration and pricing. (Member vs non-member, Student vs Academic vs Industry, etc.)<br />
any other “add-ons” that should be offered at registration.<br />
<br />
* '''Visas:''' General nervousness around Visas; we should provide a webpage with general information about what visa is required and the process for obtaining one.<br />
<br />
* '''Student volunteers:''' Karin will be coordinating the student volunteers, and communication with the Student Research Workshop organizers is underway. The objective is to offer as many students assistance as possible so we would like to avoid overlaps between those obtaining travel grants (which covers registration) and those receiving registration waivers due to volunteering. '''To do:''' set up Expression of Interest form for volunteers and circulate.<br />
<br />
* '''Childcare:''' Trevor is looking after childcare. The PCO has been looking into childcare companies at our request and it is something that can be offered. The conference would need to allocate one of its rooms for childcare, which will most likely mean having to pay for an additional room beyond what we have contracted already (according to the PCO, none of the rooms in the current contract which won’t be used for sessions/workshops/tutorials is suitable for childcare, as this wasn’t part of the original discussion with MCEC). The ratio of carer to child is 1:4 and each carer is around $60 per hour. In addition to the hourly rate, the conference would need to provide a number of materials/resources such as a microwave, fridge, TV (can be obtained from the venue), change mat plus activities such as colouring books and playdoh (activities can be purchased for a few hundred dollars). '''To do:''' Make final decision on how to proceed.<br />
<br />
== '''Business Office''' ==<br />
Priscilla Rasmussen, ACL</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723992018Q1 Reports: ACL 20182018-03-04T15:33:13Z<p>JoakimNivre: /* Local Organising Committee */</p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI ===<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
'''Thursday July 19, 2018'''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
''''Friday July 20, 2018''''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}<br />
<br />
== '''Student Research Workshop''' ==<br />
<br />
Student Organisers<br />
* Vered Shwartz, Bar-Ilan University<br />
* Jeniya Tabassum, Ohio State University<br />
* Rob Voigt, Stanford University<br />
<br />
Faculty Advisors to the Student Research Workshop<br />
* Marie-Catherine de Marneffe, Ohio State<br />
* Wanxiang Che, Harbin Institute of Technology<br />
* Malvina Nissim, University of Groningen<br />
<br />
Information about the Student Research Workshop (SRW) for ACL 2018 has been posted at the following URL: https://sites.google.com/view/aclsrw2018/ .<br />
The SRW has applied for a NSF grant of $18,000. The SRW has been awarded $6,000 by Roam analytics and $4,500 by Google. The SRW will be integrated into the main ACL conference during an evening poster session.<br />
Submission deadlines for the SRW are as follows:<br />
* Pre-submission mentoring deadline: February 26, 2018<br />
* Pre-submission mentoring feedback: March 19, 2018<br />
* Paper submission deadline: April 8, 2018<br />
* Review deadline: April 25, 2018<br />
* Acceptance notification: May 2, 2018<br />
* Camera-ready deadline: May 21, 2018<br />
* Travel grant application deadline: (Last date of Early bird registration of Conference)<br />
* Travel grant notification: (Last date of Early bird registration + 5 days)<br />
<br />
The program committee recruitment is complete, with 88 confirmed PC members. Pre-submission and post-acceptance mentors are recruited from the PC members. We have 11 Pre-submission mentors and 11 post-acceptance mentors.<br />
The SRW START site has been set up. The SRW CFP has been distributed to the following lists: ACL member portal, LINGUIST List, MT-list, comp.ai.nat-lang, Corpora, SigIR.<br />
<br />
== '''Conference Handbook Chair''' ==<br />
Jey Han Lau, IBM Research<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
We’ve read Matt Post’s “handbook chair duties” and forked the handbook source code (https://github.com/naacl-org/naacl-handbook). We are currently in discussion with Priscilla and Shiqi to finalise timeline for the handbook creation, which is detailed below. Note that the deadlines are much more compressed than last year, as this time around the deadlines for paper decisions and camera ready is much closer to the conference date. Consequently the PC and workshop organisers will need to start on scheduling before the camera ready deadlines, i.e., soon after acceptance decisions, which can be revised after camera ready (is this feasible?).<br />
<br />
At the moment we are blocking some time off from June 2-8 to work on the handbook, but this may change (depending on the discussion with Priscilla and Shiqi) because NAACL is happening that week and we anticipate that people might be busy (Trevor included). We have started working on the local guide, enlisting help from colleagues who have run conferences here in previous years, and are looking for a cover designer. We will start liaising with PC and workshop chairs soon to clarify some deadlines/expectation, once these dates are confirmed.<br />
<br />
Timeline:<br />
* 27 April: Handbook draft, excluding conference and workshop data<br />
* 25 May: Draft workshop schedules and programs<br />
* 1 June: Final main conference program due (3 weeks for PC to assemble the “order” file)<br />
* 7 June: Final workshop schedules and programs due (10 days for workshop chair to assemble the “order” file)<br />
* 14 June: Final handbook to OmniPress for printing<br />
* 12 July: Handbook arrives in Melbourne<br />
* 15 July: ACL2018 conference starts<br />
<br />
== '''Publicity Chair''' ==<br />
Sarvnaz Karimi, CSIRO<br />
<br />
The publicity effort has so far included disseminating information---including CFPs and other news items such as when the anonymity period started, or when the submission system opened--- on multiple mailing lists. All the announcements are also made on social media (Twitter and Facebook). <br />
<br />
== '''Webmaster and Appmaster''' ==<br />
Andrew MacKinlay, Culture Amp / University of Melbourne<br />
<br />
== '''Local Organising Committee''' ==<br />
Tim Baldwin, University of Melbourne<br><br />
Karin Verspoor, University of Melbourne<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
* '''Sponsorship:''' Local organizers have been receiving sponsorship inquiries and routinely responding with (a) the Sponsorship brochure provided by Priscilla, and (b) the contact information for the ACL sponsorship team. Cecile Paris and Ben Hachey are responsible for Australia-based companies; the PCO will manage the invoices and money for those local sponsorships. The PCO should also be responsible for final collection and display of logos; this is being confirmed.<br />
* '''To note:''' It is important to maintain a common list of sponsors across domestic and international sponsorships, since some sponsorship opportunities are only available to a single sponsor. (e.g. the domestic organization CSIRO has come on board as the Student Volunteer Sponsor.) This is now happening via a shared Google Spreadsheet.<br />
<br />
* '''Exhibits:''' Nothing specific to report at this stage; depends on final sponsorship numbers and commitments. Space should not be an issue.<br />
<br />
* '''Registration:''' Inquiries related to registration are steadily increasing and it would be good to open registration soon. The PCO is ready with the local hotel blocks (see below) and has estimated that it will take them 1 month to put together the registration form (which will be locally hosted, for tax reasons); now that tutorials and workshops are settled we should be able to open registration. Any reason not to go ahead ASAP? <br />
* '''Required:''' Final advice on all elements/variations for registration and pricing. (Member vs non-member, Student vs Academic vs Industry, etc.)<br />
any other “add-ons” that should be offered at registration.<br />
<br />
* '''Visas:''' General nervousness around Visas; we should provide a webpage with general information about what visa is required and the process for obtaining one.<br />
<br />
* '''Student volunteers:''' Karin will be coordinating the student volunteers, and communication with the Student Research Workshop organizers is underway. The objective is to offer as many students assistance as possible so we would like to avoid overlaps between those obtaining travel grants (which covers registration) and those receiving registration waivers due to volunteering. <br />
* '''To do:''' set up Expression of Interest form for volunteers and circulate.<br />
<br />
* '''Childcare:''' Trevor is looking after childcare. The PCO has been looking into childcare companies at our request and it is something that can be offered. The conference would need to allocate one of its rooms for childcare, which will most likely mean having to pay for an additional room beyond what we have contracted already (according to the PCO, none of the rooms in the current contract which won’t be used for sessions/workshops/tutorials is suitable for childcare, as this wasn’t part of the original discussion with MCEC). The ratio of carer to child is 1:4 and each carer is around $60 per hour. In addition to the hourly rate, the conference would need to provide a number of materials/resources such as a microwave, fridge, TV (can be obtained from the venue), change mat plus activities such as colouring books and playdoh (activities can be purchased for a few hundred dollars).<br />
* '''To do:''' Make final decision on how to proceed.<br />
<br />
== '''Business Office''' ==<br />
Priscilla Rasmussen, ACL</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723982018Q1 Reports: ACL 20182018-03-04T15:30:57Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI ===<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
'''Thursday July 19, 2018'''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
''''Friday July 20, 2018''''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}<br />
<br />
== '''Student Research Workshop''' ==<br />
<br />
Student Organisers<br />
* Vered Shwartz, Bar-Ilan University<br />
* Jeniya Tabassum, Ohio State University<br />
* Rob Voigt, Stanford University<br />
<br />
Faculty Advisors to the Student Research Workshop<br />
* Marie-Catherine de Marneffe, Ohio State<br />
* Wanxiang Che, Harbin Institute of Technology<br />
* Malvina Nissim, University of Groningen<br />
<br />
Information about the Student Research Workshop (SRW) for ACL 2018 has been posted at the following URL: https://sites.google.com/view/aclsrw2018/ .<br />
The SRW has applied for a NSF grant of $18,000. The SRW has been awarded $6,000 by Roam analytics and $4,500 by Google. The SRW will be integrated into the main ACL conference during an evening poster session.<br />
Submission deadlines for the SRW are as follows:<br />
* Pre-submission mentoring deadline: February 26, 2018<br />
* Pre-submission mentoring feedback: March 19, 2018<br />
* Paper submission deadline: April 8, 2018<br />
* Review deadline: April 25, 2018<br />
* Acceptance notification: May 2, 2018<br />
* Camera-ready deadline: May 21, 2018<br />
* Travel grant application deadline: (Last date of Early bird registration of Conference)<br />
* Travel grant notification: (Last date of Early bird registration + 5 days)<br />
<br />
The program committee recruitment is complete, with 88 confirmed PC members. Pre-submission and post-acceptance mentors are recruited from the PC members. We have 11 Pre-submission mentors and 11 post-acceptance mentors.<br />
The SRW START site has been set up. The SRW CFP has been distributed to the following lists: ACL member portal, LINGUIST List, MT-list, comp.ai.nat-lang, Corpora, SigIR.<br />
<br />
== '''Conference Handbook Chair''' ==<br />
Jey Han Lau, IBM Research<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
We’ve read Matt Post’s “handbook chair duties” and forked the handbook source code (https://github.com/naacl-org/naacl-handbook). We are currently in discussion with Priscilla and Shiqi to finalise timeline for the handbook creation, which is detailed below. Note that the deadlines are much more compressed than last year, as this time around the deadlines for paper decisions and camera ready is much closer to the conference date. Consequently the PC and workshop organisers will need to start on scheduling before the camera ready deadlines, i.e., soon after acceptance decisions, which can be revised after camera ready (is this feasible?).<br />
<br />
At the moment we are blocking some time off from June 2-8 to work on the handbook, but this may change (depending on the discussion with Priscilla and Shiqi) because NAACL is happening that week and we anticipate that people might be busy (Trevor included). We have started working on the local guide, enlisting help from colleagues who have run conferences here in previous years, and are looking for a cover designer. We will start liaising with PC and workshop chairs soon to clarify some deadlines/expectation, once these dates are confirmed.<br />
<br />
Timeline:<br />
* 27 April: Handbook draft, excluding conference and workshop data<br />
* 25 May: Draft workshop schedules and programs<br />
* 1 June: Final main conference program due (3 weeks for PC to assemble the “order” file)<br />
* 7 June: Final workshop schedules and programs due (10 days for workshop chair to assemble the “order” file)<br />
* 14 June: Final handbook to OmniPress for printing<br />
* 12 July: Handbook arrives in Melbourne<br />
* 15 July: ACL2018 conference starts<br />
<br />
== '''Publicity Chair''' ==<br />
Sarvnaz Karimi, CSIRO<br />
<br />
The publicity effort has so far included disseminating information---including CFPs and other news items such as when the anonymity period started, or when the submission system opened--- on multiple mailing lists. All the announcements are also made on social media (Twitter and Facebook). <br />
<br />
== '''Webmaster and Appmaster''' ==<br />
Andrew MacKinlay, Culture Amp / University of Melbourne<br />
<br />
== '''Local Organising Committee''' ==<br />
Tim Baldwin, University of Melbourne<br><br />
Karin Verspoor, University of Melbourne<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
* '''Sponsorship:''' Local organizers have been receiving sponsorship inquiries and routinely responding with (a) the Sponsorship brochure provided by Priscilla, and (b) the contact information for the ACL sponsorship team. Cecile Paris and Ben Hachey are responsible for Australia-based companies; the PCO will manage the invoices and money for those local sponsorships. The PCO should also be responsible for final collection and display of logos; this is being confirmed. <br />
'''To note:''' It is important to maintain a common list of sponsors across domestic and international sponsorships, since some sponsorship opportunities are only available to a single sponsor. (e.g. the domestic organization CSIRO has come on board as the Student Volunteer Sponsor.) This is now happening via a shared Google Spreadsheet.<br />
<br />
* Exhibits: Nothing specific to report at this stage; depends on final sponsorship numbers and commitments. Space should not be an issue.<br />
<br />
* Registration: Inquiries related to registration are steadily increasing and it would be good to open registration soon. The PCO is ready with the local hotel blocks (see below) and has estimated that it will take them 1 month to put together the registration form (which will be locally hosted, for tax reasons); now that tutorials and workshops are settled we should be able to open registration. Any reason not to go ahead ASAP? <br />
'''Required:''' Final advice on all elements/variations for registration and pricing. (Member vs non-member, Student vs Academic vs Industry, etc.)<br />
any other “add-ons” that should be offered at registration.<br />
<br />
* Visas: General nervousness around Visas; we should provide a webpage with general information about what visa is required and the process for obtaining one.<br />
<br />
* Student volunteers: Karin will be coordinating the student volunteers, and communication with the Student Research Workshop organizers is underway. The objective is to offer as many students assistance as possible so we would like to avoid overlaps between those obtaining travel grants (which covers registration) and those receiving registration waivers due to volunteering. <br />
'''To do:''' set up Expression of Interest form for volunteers and circulate.<br />
<br />
* Childcare: Trevor is looking after childcare. The PCO has been looking into childcare companies at our request and it is something that can be offered. The conference would need to allocate one of its rooms for childcare, which will most likely mean having to pay for an additional room beyond what we have contracted already (according to the PCO, none of the rooms in the current contract which won’t be used for sessions/workshops/tutorials is suitable for childcare, as this wasn’t part of the original discussion with MCEC). The ratio of carer to child is 1:4 and each carer is around $60 per hour. In addition to the hourly rate, the conference would need to provide a number of materials/resources such as a microwave, fridge, TV (can be obtained from the venue), change mat plus activities such as colouring books and playdoh (activities can be purchased for a few hundred dollars).<br />
'''To do:''' Make final decision on how to proceed.<br />
<br />
== '''Business Office''' ==<br />
Priscilla Rasmussen, ACL</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723962018Q1 Reports: ACL 20182018-03-02T11:23:01Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI ===<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
'''Thursday July 19, 2018'''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
''''Friday July 20, 2018''''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}<br />
<br />
== '''Student Research Workshop''' ==<br />
<br />
Student Organisers<br />
* Vered Shwartz, Bar-Ilan University<br />
* Jeniya Tabassum, Ohio State University<br />
* Rob Voigt, Stanford University<br />
<br />
Faculty Advisors to the Student Research Workshop<br />
* Marie-Catherine de Marneffe, Ohio State<br />
* Wanxiang Che, Harbin Institute of Technology<br />
* Malvina Nissim, University of Groningen<br />
<br />
Information about the Student Research Workshop (SRW) for ACL 2018 has been posted at the following URL: https://sites.google.com/view/aclsrw2018/ .<br />
The SRW has applied for a NSF grant of $18,000. The SRW has been awarded $6,000 by Roam analytics and $4,500 by Google. The SRW will be integrated into the main ACL conference during an evening poster session.<br />
Submission deadlines for the SRW are as follows:<br />
* Pre-submission mentoring deadline: February 26, 2018<br />
* Pre-submission mentoring feedback: March 19, 2018<br />
* Paper submission deadline: April 8, 2018<br />
* Review deadline: April 25, 2018<br />
* Acceptance notification: May 2, 2018<br />
* Camera-ready deadline: May 21, 2018<br />
* Travel grant application deadline: (Last date of Early bird registration of Conference)<br />
* Travel grant notification: (Last date of Early bird registration + 5 days)<br />
<br />
The program committee recruitment is complete, with 88 confirmed PC members. Pre-submission and post-acceptance mentors are recruited from the PC members. We have 11 Pre-submission mentors and 11 post-acceptance mentors.<br />
The SRW START site has been set up. The SRW CFP has been distributed to the following lists: ACL member portal, LINGUIST List, MT-list, comp.ai.nat-lang, Corpora, SigIR.<br />
<br />
== '''Conference Handbook Chair''' ==<br />
Jey Han Lau, IBM Research<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
We’ve read Matt Post’s “handbook chair duties” and forked the handbook source code (https://github.com/naacl-org/naacl-handbook). We are currently in discussion with Priscilla and Shiqi to finalise timeline for the handbook creation, which is detailed below. Note that the deadlines are much more compressed than last year, as this time around the deadlines for paper decisions and camera ready is much closer to the conference date. Consequently the PC and workshop organisers will need to start on scheduling before the camera ready deadlines, i.e., soon after acceptance decisions, which can be revised after camera ready (is this feasible?).<br />
<br />
At the moment we are blocking some time off from June 2-8 to work on the handbook, but this may change (depending on the discussion with Priscilla and Shiqi) because NAACL is happening that week and we anticipate that people might be busy (Trevor included). We have started working on the local guide, enlisting help from colleagues who have run conferences here in previous years, and are looking for a cover designer. We will start liaising with PC and workshop chairs soon to clarify some deadlines/expectation, once these dates are confirmed.<br />
<br />
Timeline:<br />
* 27 April: Handbook draft, excluding conference and workshop data<br />
* 25 May: Draft workshop schedules and programs<br />
* 1 June: Final main conference program due (3 weeks for PC to assemble the “order” file)<br />
* 7 June: Final workshop schedules and programs due (10 days for workshop chair to assemble the “order” file)<br />
* 14 June: Final handbook to OmniPress for printing<br />
* 12 July: Handbook arrives in Melbourne<br />
* 15 July: ACL2018 conference starts<br />
<br />
== '''Publicity Chair''' ==<br />
Sarvnaz Karimi, CSIRO<br />
<br />
The publicity effort has so far included disseminating information---including CFPs and other news items such as when the anonymity period started, or when the submission system opened--- on multiple mailing lists. All the announcements are also made on social media (Twitter and Facebook). <br />
<br />
== '''Webmaster and Appmaster''' ==<br />
Andrew MacKinlay, Culture Amp / University of Melbourne<br />
<br />
== '''Local Organising Committee''' ==<br />
Tim Baldwin, University of Melbourne<br><br />
Karin Verspoor, University of Melbourne<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
== '''Business Office''' ==<br />
Priscilla Rasmussen, ACL</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723952018Q1 Reports: ACL 20182018-03-02T11:21:52Z<p>JoakimNivre: /* Conference Handbook Chair */</p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI ===<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
'''Thursday July 19, 2018'''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
''''Friday July 20, 2018''''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}<br />
<br />
== '''Student Research Workshop''' ==<br />
<br />
Student Organisers<br />
* Vered Shwartz, Bar-Ilan University<br />
* Jeniya Tabassum, Ohio State University<br />
* Rob Voigt, Stanford University<br />
<br />
Faculty Advisors to the Student Research Workshop<br />
* Marie-Catherine de Marneffe, Ohio State<br />
* Wanxiang Che, Harbin Institute of Technology<br />
* Malvina Nissim, University of Groningen<br />
<br />
Information about the Student Research Workshop (SRW) for ACL 2018 has been posted at the following URL: https://sites.google.com/view/aclsrw2018/ .<br />
The SRW has applied for a NSF grant of $18,000. The SRW has been awarded $6,000 by Roam analytics and $4,500 by Google. The SRW will be integrated into the main ACL conference during an evening poster session.<br />
Submission deadlines for the SRW are as follows:<br />
* Pre-submission mentoring deadline: February 26, 2018<br />
* Pre-submission mentoring feedback: March 19, 2018<br />
* Paper submission deadline: April 8, 2018<br />
* Review deadline: April 25, 2018<br />
* Acceptance notification: May 2, 2018<br />
* Camera-ready deadline: May 21, 2018<br />
* Travel grant application deadline: (Last date of Early bird registration of Conference)<br />
* Travel grant notification: (Last date of Early bird registration + 5 days)<br />
<br />
The program committee recruitment is complete, with 88 confirmed PC members. Pre-submission and post-acceptance mentors are recruited from the PC members. We have 11 Pre-submission mentors and 11 post-acceptance mentors.<br />
The SRW START site has been set up. The SRW CFP has been distributed to the following lists: ACL member portal, LINGUIST List, MT-list, comp.ai.nat-lang, Corpora, SigIR.<br />
<br />
== '''Local Organising Committee''' ==<br />
Tim Baldwin, University of Melbourne<br><br />
Karin Verspoor, University of Melbourne<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
== '''Publicity Chair''' ==<br />
Sarvnaz Karimi, CSIRO<br />
<br />
The publicity effort has so far included disseminating information---including CFPs and other news items such as when the anonymity period started, or when the submission system opened--- on multiple mailing lists. All the announcements are also made on social media (Twitter and Facebook). <br />
<br />
== '''Webmaster and Appmaster''' ==<br />
Andrew MacKinlay, Culture Amp / University of Melbourne<br />
<br />
== '''Conference Handbook Chair''' ==<br />
Jey Han Lau, IBM Research<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
We’ve read Matt Post’s “handbook chair duties” and forked the handbook source code (https://github.com/naacl-org/naacl-handbook). We are currently in discussion with Priscilla and Shiqi to finalise timeline for the handbook creation, which is detailed below. Note that the deadlines are much more compressed than last year, as this time around the deadlines for paper decisions and camera ready is much closer to the conference date. Consequently the PC and workshop organisers will need to start on scheduling before the camera ready deadlines, i.e., soon after acceptance decisions, which can be revised after camera ready (is this feasible?).<br />
<br />
At the moment we are blocking some time off from June 2-8 to work on the handbook, but this may change (depending on the discussion with Priscilla and Shiqi) because NAACL is happening that week and we anticipate that people might be busy (Trevor included). We have started working on the local guide, enlisting help from colleagues who have run conferences here in previous years, and are looking for a cover designer. We will start liaising with PC and workshop chairs soon to clarify some deadlines/expectation, once these dates are confirmed.<br />
<br />
Timeline:<br />
* 27 April: Handbook draft, excluding conference and workshop data<br />
* 25 May: Draft workshop schedules and programs<br />
* 1 June: Final main conference program due (3 weeks for PC to assemble the “order” file)<br />
* 7 June: Final workshop schedules and programs due (10 days for workshop chair to assemble the “order” file)<br />
* 14 June: Final handbook to OmniPress for printing<br />
* 12 July: Handbook arrives in Melbourne<br />
* 15 July: ACL2018 conference starts<br />
<br />
== '''Business Office''' ==<br />
Priscilla Rasmussen, ACL</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723842018Q1 Reports: ACL 20182018-03-01T12:52:15Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI ===<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
'''Thursday July 19, 2018'''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
''''Friday July 20, 2018''''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}<br />
<br />
== '''Student Research Workshop''' ==<br />
<br />
Student Organisers<br />
* Vered Shwartz, Bar-Ilan University<br />
* Jeniya Tabassum, Ohio State University<br />
* Rob Voigt, Stanford University<br />
<br />
Faculty Advisors to the Student Research Workshop<br />
* Marie-Catherine de Marneffe, Ohio State<br />
* Wanxiang Che, Harbin Institute of Technology<br />
* Malvina Nissim, University of Groningen<br />
<br />
Information about the Student Research Workshop (SRW) for ACL 2018 has been posted at the following URL: https://sites.google.com/view/aclsrw2018/ .<br />
The SRW has applied for a NSF grant of $18,000. The SRW has been awarded $6,000 by Roam analytics and $4,500 by Google. The SRW will be integrated into the main ACL conference during an evening poster session.<br />
Submission deadlines for the SRW are as follows:<br />
* Pre-submission mentoring deadline: February 26, 2018<br />
* Pre-submission mentoring feedback: March 19, 2018<br />
* Paper submission deadline: April 8, 2018<br />
* Review deadline: April 25, 2018<br />
* Acceptance notification: May 2, 2018<br />
* Camera-ready deadline: May 21, 2018<br />
* Travel grant application deadline: (Last date of Early bird registration of Conference)<br />
* Travel grant notification: (Last date of Early bird registration + 5 days)<br />
<br />
The program committee recruitment is complete, with 88 confirmed PC members. Pre-submission and post-acceptance mentors are recruited from the PC members. We have 11 Pre-submission mentors and 11 post-acceptance mentors.<br />
The SRW START site has been set up. The SRW CFP has been distributed to the following lists: ACL member portal, LINGUIST List, MT-list, comp.ai.nat-lang, Corpora, SigIR.<br />
<br />
== '''Local Organising Committee''' ==<br />
Tim Baldwin, University of Melbourne<br><br />
Karin Verspoor, University of Melbourne<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
== '''Publicity Chair''' ==<br />
Sarvnaz Karimi, CSIRO<br />
<br />
The publicity effort has so far included disseminating information---including CFPs and other news items such as when the anonymity period started, or when the submission system opened--- on multiple mailing lists. All the announcements are also made on social media (Twitter and Facebook). <br />
<br />
== '''Webmaster and Appmaster''' ==<br />
Andrew MacKinlay, Culture Amp / University of Melbourne<br />
<br />
== '''Conference Handbook Chair''' ==<br />
Jey Han Lau, IBM Research<br />
Trevor Cohn, University of Melbourne<br />
<br />
== '''Business Office''' ==<br />
Priscilla Rasmussen, ACL</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723832018Q1 Reports: ACL 20182018-03-01T12:51:43Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI ===<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
'''Thursday July 19, 2018'''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
''''Friday July 20, 2018''''<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}<br />
<br />
== '''Student Research Workshop''' ==<br />
<br />
Student Organisers<br />
* Vered Shwartz, Bar-Ilan University<br />
* Jeniya Tabassum, Ohio State University<br />
* Rob Voigt, Stanford University<br />
<br />
Faculty Advisors to the Student Research Workshop<br />
* Marie-Catherine de Marneffe, Ohio State<br />
* Wanxiang Che, Harbin Institute of Technology<br />
* Malvina Nissim, University of Groningen<br />
<br />
Information about the Student Research Workshop (SRW) for ACL 2018 has been posted at the following URL: https://sites.google.com/view/aclsrw2018/ .<br />
The SRW has applied for a NSF grant of $18,000. The SRW has been awarded $6,000 by Roam analytics and $4,500 by Google. The SRW will be integrated into the main ACL conference during an evening poster session.<br />
Submission deadlines for the SRW are as follows:<br />
* Pre-submission mentoring deadline: February 26, 2018<br />
* Pre-submission mentoring feedback: March 19, 2018<br />
* Paper submission deadline: April 8, 2018<br />
* Review deadline: April 25, 2018<br />
* Acceptance notification: May 2, 2018<br />
* Camera-ready deadline: May 21, 2018<br />
* Travel grant application deadline: (Last date of Early bird registration of Conference)<br />
* Travel grant notification: (Last date of Early bird registration + 5 days)<br />
<br />
The program committee recruitment is complete, with 88 confirmed PC members. Pre-submission and post-acceptance mentors are recruited from the PC members. We have 11 Pre-submission mentors and 11 post-acceptance mentors.<br />
The SRW START site has been set up. The SRW CFP has been distributed to the following lists: ACL member portal, LINGUIST List, MT-list, comp.ai.nat-lang, Corpora, SigIR.<br />
<br />
== '''Local Organising Committee'''' ==<br />
Tim Baldwin, University of Melbourne<br><br />
Karin Verspoor, University of Melbourne<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
== '''Publicity Chair''' ==<br />
Sarvnaz Karimi, CSIRO<br />
<br />
The publicity effort has so far included disseminating information---including CFPs and other news items such as when the anonymity period started, or when the submission system opened--- on multiple mailing lists. All the announcements are also made on social media (Twitter and Facebook). <br />
<br />
== '''Webmaster and Appmaster''' ==<br />
Andrew MacKinlay, Culture Amp / University of Melbourne<br />
<br />
== '''Conference Handbook Chair'''' ==<br />
Jey Han Lau, IBM Research<br />
Trevor Cohn, University of Melbourne<br />
<br />
== '''Business Office'''' ==<br />
Priscilla Rasmussen, ACL</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723822018Q1 Reports: ACL 20182018-03-01T12:49:23Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI ===<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
=== Thursday July 19, 2018 ===<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
=== Friday July 20, 2018 ===<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}<br />
<br />
== '''Student Research Workshop''' ==<br />
<br />
Student Organisers<br />
* Vered Shwartz, Bar-Ilan University<br />
* Jeniya Tabassum, Ohio State University<br />
* Rob Voigt, Stanford University<br />
<br />
Faculty Advisors to the Student Research Workshop<br />
* Marie-Catherine de Marneffe, Ohio State<br />
* Wanxiang Che, Harbin Institute of Technology<br />
* Malvina Nissim, University of Groningen<br />
<br />
Information about the Student Research Workshop (SRW) for ACL 2018 has been posted at the following URL: https://sites.google.com/view/aclsrw2018/ .<br />
The SRW has applied for a NSF grant of $18,000. The SRW has been awarded $6,000 by Roam analytics and $4,500 by Google. The SRW will be integrated into the main ACL conference during an evening poster session.<br />
Submission deadlines for the SRW are as follows:<br />
* Pre-submission mentoring deadline: February 26, 2018<br />
* Pre-submission mentoring feedback: March 19, 2018<br />
* Paper submission deadline: April 8, 2018<br />
* Review deadline: April 25, 2018<br />
* Acceptance notification: May 2, 2018<br />
* Camera-ready deadline: May 21, 2018<br />
* Travel grant application deadline: (Last date of Early bird registration of Conference)<br />
* Travel grant notification: (Last date of Early bird registration + 5 days)<br />
<br />
The program committee recruitment is complete, with 88 confirmed PC members. Pre-submission and post-acceptance mentors are recruited from the PC members. We have 11 Pre-submission mentors and 11 post-acceptance mentors.<br />
The SRW START site has been set up. The SRW CFP has been distributed to the following lists: ACL member portal, LINGUIST List, MT-list, comp.ai.nat-lang, Corpora, SigIR.<br />
<br />
== '''Local Organising Committee''''<br />
Tim Baldwin, University of Melbourne<br><br />
Karin Verspoor, University of Melbourne<br><br />
Trevor Cohn, University of Melbourne<br />
<br />
== '''Publicity Chair''' ==<br />
Sarvnaz Karimi, CSIRO<br />
<br />
The publicity effort has so far included disseminating information---including CFPs and other news items such as when the anonymity period started, or when the submission system opened--- on multiple mailing lists. All the announcements are also made on social media (Twitter and Facebook). <br />
<br />
== '''Webmaster and Appmaster''' ==<br />
<br />
== '''Conference Handbook Chair''''<br />
Jey Han Lau, IBM Research<br />
Trevor Cohn, University of Melbourne<br />
<br />
== '''Business Office''''<br />
Priscilla Rasmussen, ACL</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723812018Q1 Reports: ACL 20182018-03-01T12:42:22Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
=== Thursday July 19, 2018 ===<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
=== Friday July 20, 2018 ===<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723802018Q1 Reports: ACL 20182018-03-01T12:41:03Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
=== Thursday July 19, 2018 ===<br />
<br />
{|<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
=== Friday July 20, 2018 ===<br />
<br />
{|<br />
| Abbreviation<br />
| Title<br />
| Organizers<br />
| Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723792018Q1 Reports: ACL 20182018-03-01T12:39:18Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.) Here are the 15 selected workshops / colocated conferences:<br />
<br />
{|<br />
|+ Thursday July 19, 2018<br />
|-<br />
! Abbreviation<br />
! Title<br />
! Organizers<br />
! Website<br />
|-<br />
| BioNLP<br />
| BioNLP 2018<br />
| Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
| https://aclweb.org/aclwiki/BioNLP_Workshop<br />
|-<br />
| DLNLPLR<br />
| Deep Learning Approaches for Low Resource Natural Language Processing<br />
| Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
| https://sites.google.com/site/dlnlplr18/home<br />
|-<br />
| CALCS<br />
| Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
| Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
| https://code-switching.github.io/2018/<br />
|-<br />
| MSR<br />
| Multilingual Surface Realization: Shared Task and Beyond<br />
| Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
| http://taln.upf.edu/pages/msr2018-ws/<br />
|-<br />
| NLPTEA<br />
| The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
| Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
| https://sites.google.com/view/nlptea2018<br />
|-<br />
| CogCL<br />
| Cognitive Aspects of Computational Language Learning and Processing<br />
| Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
| https://sites.google.com/view/cognitivews2018/home<br />
|-<br />
| RELNLP<br />
| Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
| Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
| https://sites.google.com/view/relsnnlp<br />
|-<br />
| MRQA<br />
| Workshop on Machine Reading for Question Answering<br />
| Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
| https://mrqa2018.github.io/<br />
|}<br />
<br />
{|<br />
|+ Friday July 20, 2018<br />
|- <br />
| Abbreviation<br />
| Title<br />
| Organizers<br />
| Website<br />
|-<br />
| ECONLP<br />
| 1st Workshop on Economics and Natural Language Processing<br />
| Udo Hahn and Ming-Feng Tsai<br />
| http://www.julielab.de/econlp2018.html<br />
|-<br />
| NEWS<br />
| The Seventh Named Entities Workshop<br />
| Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
| http://workshop.colips.org/news2018/<br />
|-<br />
| NLPOSS<br />
| Workshop for NLP Open Source Software<br />
| Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
| https://nlposs.github.io/<br />
|-<br />
| SocialNLP<br />
| Sixth International Workshop on Natural Language Processing for Social Media<br />
| Lun-Wei Ku and Cheng-Te Li<br />
| https://sites.google.com/site/socialnlp2018/<br />
|-<br />
| MML_Challenge<br />
| First Workshop on Computational Modeling of Human Multimodal Language<br />
| AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
| http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
|-<br />
| RepL4NLP<br />
| 3rd Workshop on Representation Learning for NLP<br />
| Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
| https://sites.google.com/site/repl4nlp2018/<br />
|-<br />
| NMT<br />
| The 2nd Workshop on Neural Machine Translation and Generation<br />
| Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
| https://sites.google.com/site/wnmt18/<br />
|}</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723782018Q1 Reports: ACL 20182018-03-01T12:34:21Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.<br />
<br />
== '''Workshop Chairs''' ==<br />
Brendan O’Connor, University of Massachusetts Amherst<br><br />
Eva Maria Vecchi, University of Stuttgart / University of Cambridge<br />
<br />
The workshop chairs selected 15 workshops to be held immediately following the ACL 2018 conference. There will be one additional workshop - the Student Research Workshop (SRW) which will be held during one of the evening poster sessions during the main conference.<br />
The workshops were selected using a joint call and review procedure, as a joint committee comprised of the workshop organizers of the 2018 editions of ACL, NAACL, COLING and EMNLP. The workshop review process followed the procedure of the previous year, namely:<br />
Each of the workshop proposals was initially reviewed by 2 members of the committee in the SoftConf system, with numerical scores and textual comments and most committee members reviewing around 15 proposals. To aid in the review process, we attempted to first categorize the workshop proposals, to help align proposals with areas of expertise on the committee. This categorization proved quite difficult because many proposals intentionally spanned several disciplines, but it did help identify proposals that were similar.<br />
As was done last year, we also conducted a web-based survey to ACL members to compare the popularity of workshops on similar topics and first-time workshops, as well as the past attendance numbers if available.<br />
<br />
Before considering the bulk of the 58 submissions, we note that there are a handful of large, long-standing workshops that the ACL organization agrees to pre-admit, including *SEM, WMT, CoNLL, and SemEval. These were all placed at their first-choice venue.<br />
<br />
Workshop proposers marked a first and second choice of conference; the workshops we accepted to ACL all had ACL as their first choice. (Two other submissions that had their first choice as ACL were instead accepted to their second choice. One submission with ACL as a first choice was rejected. 14 other submissions had ACL as a second choice; none of them was assigned to ACL.)<br />
Here are the 15 selected workshops / colocated conferences:<br />
<br />
Thursday July 19, 2018<br />
Abbreviation<br />
Title<br />
Organizers<br />
Website<br />
BioNLP<br />
BioNLP 2018<br />
Kevin Bretonnel Cohen, Dina Demner-Fushman, Sophia Ananiadou, and Jun-ichi Tsujii<br />
https://aclweb.org/aclwiki/BioNLP_Workshop<br />
DLNLPLR<br />
Deep Learning Approaches for Low Resource Natural Language Processing<br />
Reza Haffari, Colin Cherry, George Foster, Shahram Khadivi, Bahar Salehi<br />
https://sites.google.com/site/dlnlplr18/home<br />
CALCS<br />
Third Workshop on Computational Approaches to Linguistic Code-Switching<br />
Gustavo Aguilar, Fahad AlGhamdi, Victor Soto, Thamar Solorio, Mona Diab, Julia Hirschberg <br />
https://code-switching.github.io/2018/<br />
MSR<br />
Multilingual Surface Realization: Shared Task and Beyond<br />
Simon Mille, Bernd Bohnet, Leo Wanner, Anya Belz, Emily Pitler<br />
http://taln.upf.edu/pages/msr2018-ws/<br />
NLPTEA<br />
The 5th Workshop on Natural Language Processing Techniques for Educational Applications<br />
Yuen-Hsien Tseng, Hsin-Hsi Chen, Vincent Ng, Mamoru Komachi<br />
https://sites.google.com/view/nlptea2018<br />
CogCL<br />
Cognitive Aspects of Computational Language Learning and Processing<br />
Marco Idiart, Alessandro Lenci, Thierry Poibeau and Aline Villavicencio<br />
https://sites.google.com/view/cognitivews2018/home<br />
RELNLP<br />
Workshop on Relevance of Linguistic Structure in Neural Architectures for NLP<br />
Georgiana Dinu, Miguel Ballesteros, Yoav Goldberg, Avirup Sil, Tahira Naseem, Samuel Bowman, Wael Hamza, Anders Sogaard and Radu Florian<br />
https://sites.google.com/view/relsnnlp<br />
MRQA<br />
Workshop on Machine Reading for Question Answering<br />
Eunsol Choi, Minjoon Seo, Danqi Chen, Robin Jia and Jonathan Berant<br />
https://mrqa2018.github.io/<br />
<br />
Friday July 20, 2018<br />
Abbreviation<br />
Title<br />
Organizers<br />
Website<br />
ECONLP<br />
1st Workshop on Economics and Natural Language Processing<br />
Udo Hahn and Ming-Feng Tsai<br />
http://www.julielab.de/econlp2018.html<br />
NEWS<br />
The Seventh Named Entities Workshop<br />
Nancy Chen, Xiangyu Duan, Rafael E. Banchs, Min Zhang and Haizhou Li<br />
http://workshop.colips.org/news2018/<br />
NLPOSS<br />
Workshop for NLP Open Source Software<br />
Masato Hagiwara, Dmitrijs Milajevs, Eunjeong Park and Liling Tan<br />
https://nlposs.github.io/<br />
SocialNLP<br />
Sixth International Workshop on Natural Language Processing for Social Media<br />
Lun-Wei Ku and Cheng-Te Li<br />
https://sites.google.com/site/socialnlp2018/<br />
MML_Challenge<br />
First Workshop on Computational Modeling of Human Multimodal Language<br />
AmirAli Bagher Zadeh, Louis-Philippe Morency, Soujanya Poria, Erik Cambria, Stefan Scherer and Paul Liang<br />
http://multicomp.cs.cmu.edu/acl2018multimodalchallenge/<br />
RepL4NLP<br />
3rd Workshop on Representation Learning for NLP<br />
Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Ryan Kiros, Hongyuan Mei and Dipendra Misra<br />
https://sites.google.com/site/repl4nlp2018/<br />
NMT<br />
The 2nd Workshop on Neural Machine Translation and Generation<br />
Alexandra Birch, Andrew Finch, Minh-Thang Luong, Graham Neubig and Yusuke Oda<br />
https://sites.google.com/site/wnmt18/</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723772018Q1 Reports: ACL 20182018-03-01T12:32:50Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI<br />
<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723762018Q1 Reports: ACL 20182018-03-01T12:31:20Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site<br />
<br />
== '''Tutorial Chairs''' ==<br />
Yoav Artzi, Cornell University <br><br />
Jacob Eisenstein, Georgia Institute of Technology<br />
<br />
In total, we received 49 submissions for the joint ACL/COLING/NAACL/EMNLP call, and we accepted 28 of them. 28 tutorials had ACL as the preferred conference: 13 were rejected, 6 were selected for their alternative choice, and the rest were accepted. Eight tutorials were selected for ACL:<br />
<br />
1. Neural Approaches to Conversational AI<br />
Jianfeng Gao, Michel Galley and Lihong Li<br />
<br />
Developing an intelligent dialogue system that not only emulates human conversation, but also can answer questions of topics ranging from latest news of a movie star to Einstein's theory of relativity, and fulfill complex tasks such as travel planning, has been one of the longest running goals in AI. The goal remains elusive until recently when we started observing promising results in both the research community and industry as the large amount of conversation data is available for training and the breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.<br />
In this tutorial, we start with a brief introduction to the recent progress on DL and RL that is related to natural language processing and conversational AI. Then, we describe in detail the state-of-the-art neural approaches developed for three types of dialogue systems. The first is a question answering (QA) agent. Equipped with rich knowledge drawn from various data sources including Web documents and pre-complied knowledge graphs (KG's), the QA agent can provide concise direct answers to user queries. The second is a task-oriented dialogue system that can help users accomplish tasks ranging from meeting scheduling to vacation planning. The third is a social chat bot which can converse seamlessly and appropriately with humans, and often plays roles of a chat companion and a recommender. In the final part of the tutorial, we review attempts to developing open-domain conversational AI systems that combine the strengths of different types of dialogue systems.<br />
<br />
2. Deep Reinforcement Learning for NLP<br />
William Yang Wang, Jiwei Li and Xiaodong He<br />
<br />
Many Natural Language Processing (NLP) tasks (including generation, language grounding, reasoning, information extraction, coreference resolution, and dialog) can be formulated as deep reinforcement learning (DRL) problems. However, since language is often discrete and the space for all sentences is infinite, there are many challenges for formulating reinforcement learning problems of NLP tasks. In this tutorial, we provide a gentle introduction to the foundation of deep reinforcement learning, as well as some practical DRL solutions in NLP. We describe recent advances in designing deep reinforcement learning for NLP, with a special focus on generation, dialogue, and information extraction. Finally, we discuss why they succeed, and when they may fail, aiming at providing some practical advice about deep reinforcement learning for solving real-world NLP problems.<br />
<br />
3. Neural Semantic Parsing<br />
Luke Zettlemoyer, Matt Gardner, Pradeep Dasigi, Srinivasan Iyer and Alane Suhr<br />
<br />
Semantic parsers translate natural language utterances into machine-executable logical forms or programs, and are thus key components in natural language understanding systems. Semantic parsing is a well-established research area, with application in areas such as question answering, instruction following, voice assistants, and code generation. In the last two years, the models used for semantic parsing have changed dramatically,with the introduction of neural methods that allow us to rethink many of the previous assumptions underlying semantic parsing.<br />
Traditionally, the executable formalisms and models used in semantic parsing research have been heavily reliant on notions of formal semantics in linguistics, such as λ-calculus generated by a CCG parser. However, recent work with neural encoder-decoder semantic parsers allow for more accessible formalisms, such as standard programming languages, and NMT-style models that are much more approachable to a broader NLP audience. We will present an overview of modern neural methods for semantic parsing and how they have changed semantic parsing research.<br />
<br />
4. Beyond Multiword Expressions: Processing Idioms and Metaphors<br />
Valia Kordoni<br />
<br />
Idioms and metaphors are characteristic to all areas of human activity and to all types of discourse. Their processing is a rapidly growing area in NLP, since they have become a big challenge for NLP systems. Their omnipresence in language has been established in a number of corpus studies and the role they play in human reasoning has also been confirmed in psychological experiments. This makes idioms and metaphors an important research area for computational and cognitive linguistics, and their automatic identification and interpretation indispensable for any semantics-oriented NLP application.<br />
This tutorial aims to provide attendees with a clear notion of the linguistic characteristics of idioms and metaphors, computational models of idioms and metaphors using state-of-the-art NLP techniques, their relevance for the intersection of deep learning and natural language processing, what methods and resources are available to support their use, and what more could be done in the future. Our target audience are researchers and practitioners in machine learning, parsing (syntactic and semantic) and language technology, not necessarily experts in idioms and metaphors, who are interested in tasks that involve or could benefit from considering idioms and metaphors as a pervasive phenomenon in human language and communication.<br />
<br />
5. Connecting Language and Vision to Actions<br />
Peter Anderson, Abhishek Das and Qi Wu<br />
<br />
A long-term goal of AI research is to build intelligent agents that can see the rich visual environment around us, communicate this understanding in natural language to humans and other agents, and act in a physical or embodied environment. To this end, recent advances at the intersection of language and vision have made incredible progress -- from being able to generate natural language descriptions of images/videos, to answering questions about them, to even holding free-form conversations about visual content! However, while these agents can passively describe images or answer (a sequence of) questions about them, they cannot act in the world (what if I cannot answer a question from my current view, or I am asked to move or manipulate something?). Thus, the challenge now is to extend this progress in language and vision to embodied agents that take actions and actively interact with their visual environments. To reduce the entry barrier for new researchers, this tutorial will provide an overview of the growing number of multimodal tasks and datasets that combine textual and visual understanding. We will comprehensively review existing state-of-the-art approaches to selected tasks such as image captioning, visual question answering (VQA) and visual dialog, presenting the key architectural building blocks (such as co-attention) and novel algorithms (such as cooperative/adversarial games) used to train models for these tasks. We will then discuss some of the current and upcoming challenges of combining language, vision and actions, and introduce some recently-released interactive 3D simulation environments designed for this purpose.<br />
<br />
6. 100 Things You Always Wanted to Know about Semantics & Pragmatics But Were Afraid to Ask<br />
Emily M. Bender<br />
<br />
Meaning is a fundamental concept in Natural Language Processing (NLP), given its aim to build systems that mean what they say to you, and understand what you say to them. In order for NLP to scale beyond partial, task-specific solutions, it must be informed by what is known about how humans use language to express and understand communicative intents. The purpose of this tutorial is to present a selection of useful information about semantics and pragmatics, as understood in linguistics, in a way that's accessible to and useful for NLP practitioners with minimal (or even no) prior training in linguistics. The tutorial content is based on a manuscript in progress I am co-authoring with Prof. Alex Lascarides of the University of Edinburgh.<br />
<br />
7. Multi-lingual Entity Discovery and Linking<br />
Avirup Sil, Heng Ji, Dan Roth and Silviu-Petru Cucerzan<br />
<br />
The primary goals of this tutorial are to review the framework of cross-lingual EL and motivate it as a broad paradigm for the Information Extraction task. We will start by discussing the traditional EL techniques and metrics and address questions relevant to the adequacy of these to across domains and languages. We will then present more recent approaches such as Neural EL, discuss the basic building blocks of a state-of-the-art neural EL system and analyze some of the current results on English EL. We will then proceed to Cross-lingual EL and discuss methods that work across languages. In particular, we will discuss and compare multiple methods that make use of multi-lingual word embeddings. We will also present EL methods that work for both name tagging and linking in very low resource languages. Finally, we will discuss the uses of cross-lingual EL in a variety of applications like search engines and commercial product selling applications. Also, contrary to the 2014 EL tutorial, we will also focus on Entity Discovery which is an essential component of EL.<br />
<br />
8. Variational Inference and Deep Generative Models<br />
Wilker Aziz and Philip Schulz<br />
<br />
NLP has seen a surge in neural network models in recent years. These models provide state-of-the-art performance on many supervised tasks. Unsupervised and semi-supervised learning has only been addressed scarcely, however. Deep generative models (DGMs) make it possible to integrate neural networks with probabilistic graphical models. Using DGMs one can easily design latent variable models that account for missing observations and thereby enable unsupervised and semi-supervised learning with neural networks. The method of choice for training these models is variational inference.<br />
This tutorial offers a general introduction to variational inference followed by a thorough and example-driven discussion of how to use variational methods for training DGMs. It provides both the mathematical background necessary for deriving the learning algorithms as well as practical implementation guidelines. Importantly, the tutorial will cover models with continuous and discrete variables. We provide practical coding exercises implemented in IPython notebooks as well as short notes on the more intricate mathematical details that the audience can use as a reference after the tutorial. We expect that with these additional materials the tutorial will have a long-lasting impact on the community.</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723752018Q1 Reports: ACL 20182018-03-01T12:28:32Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br><br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: http://acl2018.org/2017/09/06/call-for-nominations/. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
* Asli Celikyilma (senior chair)<br />
* Verena Rieser (senior chair)<br />
* Milica Gasic<br />
* Jason Williams<br />
<br />
Discourse and Pragmatics:<br />
* Manfred Stede<br />
* Ani Nenkova (senior chair)<br />
<br />
Document Analysis:<br />
* Hang Li (senior chair)<br />
* Yiqun Liu <br />
* Eugene Agichtein<br />
<br />
Generation:<br />
* Ioannis Konstas<br />
* Claire Gardent (senior chair)<br />
<br />
Information Extraction and Text Mining:<br />
* Feiyu Xu<br />
* Kevin Cohen<br />
* Zhiyuan Liu<br />
* Ralph Grishman (senior chair)<br />
* Yi Yang<br />
* Nazli Goharian<br />
<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
* Shuly Wintner (senior chair)<br />
* Tim O'Donnell (senior chair)<br />
<br />
Machine Learning:<br />
* Andre Martins<br />
* Ariadna Quattoni<br />
* Jun Suzuki (senior chair)<br />
<br />
Machine Translation:<br />
* Yang Liu<br />
* Matt Post (senior chair)<br />
* Lucia Specia<br />
* Dekai Wu<br />
<br />
Multidisciplinary (also for AC COI):<br />
* Yoav Goldberg<br />
* Anders Søgaard<br />
* Mirella Lapata<br />
<br />
Multilinguality:<br />
* Bernardo Magnini (senior chair)<br />
<br />
Phonology, Morphology and Word Segmentation:<br />
* Graham Neubig<br />
* Hai Zhao (senior chair)<br />
* Question Answering:<br />
* Lluís Màrquez (senior chair)<br />
* Teruko Mitamura<br />
* Zornitsa Kozareva<br />
* Richard Socher<br />
<br />
Resources and Evaluation:<br />
* Gerard de Melo<br />
* Karën Fort (senior chair)<br />
* Sara Tonelli<br />
<br />
Sentence-level Semantics:<br />
* Luke Zettlemoyer (senior chair)<br />
* Ellie Pavlick<br />
* Jacob Uszkoreit<br />
<br />
Sentiment Analysis and Argument Mining:<br />
* Smaranda Muresan<br />
* Benno Stein<br />
* Yulan He (senior chair)<br />
<br />
Social Media:<br />
* David Jurgens<br />
* Jing Jiang (Senior Chair)<br />
<br />
Summarization:<br />
* Kathleen McKeown (senior chair)<br />
* Xiaodan Zhu<br />
<br />
Tagging, Chunking, Syntax and Parsing:<br />
* Liang Huang (senior chair)<br />
* Weiwei Sun<br />
* Željko Agić<br />
* Yue Zhang<br />
<br />
Textual Inference and Other Areas of Semantics:<br />
* Michael Roth (senior chair)<br />
* Fabio Massimo Zanzotto (senior chair)<br />
<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
* Yoav Artzi (senior chair)<br />
* Shinji Watanabe<br />
* Timothy Hospedales<br />
<br />
Word-level Semantics:<br />
* Ekaterina Shutova<br />
* Roberto Navigli (senior chair)<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
* March 26th–28th, 2018 Author Response Period<br />
* April 20th, 2018 Notification of Acceptance<br />
* May 11th, 2018 Camera-ready Due<br />
* July 15th, 2018 Tutorials<br />
* July 16th–18th, 2018 Main Conference<br />
* July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
* Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
* Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available (http://acl2018.org/2018/02/20/sample-review-form/).<br />
<br />
Summary of upcoming tasks<br />
* Finish area re-assignments and desk rejects<br />
* Initiate the review process<br />
* Publish statistics on submissions<br />
* Initiate Author response period<br />
* Collect decisions from ACs<br />
* Elicit meta-reviews<br />
* Decide border cases<br />
* Publish notification of acceptance<br />
* Update financial picture<br />
* Integrate TACL papers<br />
* Collect camera ready submissions<br />
* Create the conference program<br />
* Recruit session chairs<br />
* Compile statistics for ACL wiki + business meeting<br />
* Compile report<br />
* Publish updates on the ACL web site</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723742018Q1 Reports: ACL 20182018-03-01T12:25:16Z<p>JoakimNivre: /* General Chair */</p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: [http://acl2018.org/2017/09/06/call-for-nominations/]. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
Asli Celikyilma (senior chair)<br />
Verena Rieser (senior chair)<br />
Milica Gasic<br />
Jason Williams<br />
Discourse and Pragmatics:<br />
Manfred Stede<br />
Ani Nenkova (senior chair)<br />
Document Analysis:<br />
Hang Li (senior chair)<br />
Yiqun Liu <br />
Eugene Agichtein<br />
Generation:<br />
Ioannis Konstas<br />
Claire Gardent (senior chair)<br />
Information Extraction and Text Mining:<br />
Feiyu Xu<br />
Kevin Cohen<br />
Zhiyuan Liu<br />
Ralph Grishman (senior chair)<br />
Yi Yang<br />
Nazli Goharian<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
Shuly Wintner (senior chair)<br />
Tim O'Donnell (senior chair)<br />
Machine Learning:<br />
Andre Martins<br />
Ariadna Quattoni<br />
Jun Suzuki (senior chair)<br />
Machine Translation:<br />
Yang Liu<br />
Matt Post (senior chair)<br />
Lucia Specia<br />
Dekai Wu<br />
Multidisciplinary (also for AC COI):<br />
Yoav Goldberg<br />
Anders Søgaard<br />
Mirella Lapata<br />
Multilinguality:<br />
Bernardo Magnini (senior chair)<br />
Phonology, Morphology and Word Segmentation:<br />
Graham Neubig<br />
Hai Zhao (senior chair)<br />
Question Answering:<br />
Lluís Màrquez (senior chair)<br />
Teruko Mitamura<br />
Zornitsa Kozareva<br />
Richard Socher<br />
Resources and Evaluation:<br />
Gerard de Melo<br />
Karën Fort (senior chair)<br />
Sara Tonelli<br />
Sentence-level Semantics:<br />
Luke Zettlemoyer (senior chair)<br />
Ellie Pavlick<br />
Jacob Uszkoreit<br />
Sentiment Analysis and Argument Mining:<br />
Smaranda Muresan<br />
Benno Stein<br />
Yulan He (senior chair)<br />
Social Media:<br />
David Jurgens<br />
Jing Jiang (Senior Chair)<br />
Summarization:<br />
Kathleen McKeown (senior chair)<br />
Xiaodan Zhu<br />
Tagging, Chunking, Syntax and Parsing:<br />
Liang Huang (senior chair)<br />
Weiwei Sun<br />
Željko Agić<br />
Yue Zhang<br />
Textual Inference and Other Areas of Semantics:<br />
Michael Roth (senior chair)<br />
Fabio Massimo Zanzotto (senior chair)<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
Yoav Artzi (senior chair)<br />
Shinji Watanabe<br />
Timothy Hospedales<br />
Word-level Semantics:<br />
Ekaterina Shutova<br />
Roberto Navigli (senior chair)<br />
<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
March 26th–28th, 2018 Author Response Period<br />
April 20th, 2018 Notification of Acceptance<br />
May 11th, 2018 Camera-ready Due<br />
July 15th, 2018 Tutorials<br />
July 16th–18th, 2018 Main Conference<br />
July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available ( http://acl2018.org/2018/02/20/sample-review-form/ ).<br />
<br />
Summary of upcoming tasks<br />
Finish area re-assignments and desk rejects<br />
Initiate the review process<br />
Publish statistics on submissions<br />
Initiate Author response period<br />
Collect decisions from ACs<br />
Elicit meta-reviews<br />
Decide border cases<br />
Publish notification of acceptance<br />
Update financial picture<br />
Integrate TACL papers<br />
Collect camera ready submissions<br />
Create the conference program<br />
Recruit session chairs<br />
Compile statistics for ACL wiki + business meeting<br />
Compile report<br />
Publish updates on the ACL web site</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723732018Q1 Reports: ACL 20182018-03-01T12:23:37Z<p>JoakimNivre: </p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw)). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!<br />
<br />
== '''Program Co-Chairs''' ==<br />
Iryna Gurevych, TU Darmstadt<br />
Yusuke Miyao, National Institute of Informatics<br />
<br />
This year, the program co-chairs requested nominations from the community for area chairs, reviewers and invited speakers through an open call publicized in the Latest News section of the ACL 2018 website: [http://acl2018.org/2017/09/06/call-for-nominations/]. <br />
<br />
They recruited 61 area chairs for 21 areas, including 1-2 senior chairs per area. The senior chairs are responsible for maintaining the overall process of reviewing in each area, while each area chair is assigned around 30 submissions and is responsible for managing reviews for the assigned submissions.<br />
<br />
Dialogue and Interactive Systems:<br />
Asli Celikyilma (senior chair)<br />
Verena Rieser (senior chair)<br />
Milica Gasic<br />
Jason Williams<br />
Discourse and Pragmatics:<br />
Manfred Stede<br />
Ani Nenkova (senior chair)<br />
Document Analysis:<br />
Hang Li (senior chair)<br />
Yiqun Liu <br />
Eugene Agichtein<br />
Generation:<br />
Ioannis Konstas<br />
Claire Gardent (senior chair)<br />
Information Extraction and Text Mining:<br />
Feiyu Xu<br />
Kevin Cohen<br />
Zhiyuan Liu<br />
Ralph Grishman (senior chair)<br />
Yi Yang<br />
Nazli Goharian<br />
Linguistic Theories, Cognitive Modeling and Psycholinguistics:<br />
Shuly Wintner (senior chair)<br />
Tim O'Donnell (senior chair)<br />
Machine Learning:<br />
Andre Martins<br />
Ariadna Quattoni<br />
Jun Suzuki (senior chair)<br />
Machine Translation:<br />
Yang Liu<br />
Matt Post (senior chair)<br />
Lucia Specia<br />
Dekai Wu<br />
Multidisciplinary (also for AC COI):<br />
Yoav Goldberg<br />
Anders Søgaard<br />
Mirella Lapata<br />
Multilinguality:<br />
Bernardo Magnini (senior chair)<br />
Phonology, Morphology and Word Segmentation:<br />
Graham Neubig<br />
Hai Zhao (senior chair)<br />
Question Answering:<br />
Lluís Màrquez (senior chair)<br />
Teruko Mitamura<br />
Zornitsa Kozareva<br />
Richard Socher<br />
Resources and Evaluation:<br />
Gerard de Melo<br />
Karën Fort (senior chair)<br />
Sara Tonelli<br />
Sentence-level Semantics:<br />
Luke Zettlemoyer (senior chair)<br />
Ellie Pavlick<br />
Jacob Uszkoreit<br />
Sentiment Analysis and Argument Mining:<br />
Smaranda Muresan<br />
Benno Stein<br />
Yulan He (senior chair)<br />
Social Media:<br />
David Jurgens<br />
Jing Jiang (Senior Chair)<br />
Summarization:<br />
Kathleen McKeown (senior chair)<br />
Xiaodan Zhu<br />
Tagging, Chunking, Syntax and Parsing:<br />
Liang Huang (senior chair)<br />
Weiwei Sun<br />
Željko Agić<br />
Yue Zhang<br />
Textual Inference and Other Areas of Semantics:<br />
Michael Roth (senior chair)<br />
Fabio Massimo Zanzotto (senior chair)<br />
Vision, Robotics, Multimodal, Grounding and Speech:<br />
Yoav Artzi (senior chair)<br />
Shinji Watanabe<br />
Timothy Hospedales<br />
Word-level Semantics:<br />
Ekaterina Shutova<br />
Roberto Navigli (senior chair)<br />
<br />
<br />
The call for nominations posted in September 2017 resulted in 752 responses in total. Regarding the area chairs, out of 388 valid nominations, 299 unique persons were suggested; 110 persons were self-nominations. About 70% of the final area chairs were nominated by the community. We collected 936 valid nominations for reviewers. At the PhD level, 139 persons were self-nominations and 129 were nominated by others. At the PostDoc/Ass.Prof. level, 160 were self-nominated, 112 nominated by others. At the Prof. level, 221 persons were self-nominated, 175 nominated by others. We also received 138 unique nominations for invited speakers.<br />
<br />
As in ACL 2017, we introduced a special area for handling COI of area chairs. The strategy is that if AC has a COI in their area, we try to find another area that still fits the paper well. If this is not the case, the paper is moved to the “Multidisciplinary / COI” area. This area is handled by experienced area chairs.<br />
<br />
Right after the submission deadline, there are 1045 long and 576 short papers. Several submissions have already been identified as desk reject, but the program chairs and area chairs are still working on cleaning them up at the moment. Areas with more than a hundred submissions include: Information Extraction and Text Mining, Machine Learning, Machine Translation, Document Analysis, and Dialogue and Interactive Systems.<br />
<br />
Summary of upcoming deadlines:<br />
March 26th–28th, 2018 Author Response Period<br />
April 20th, 2018 Notification of Acceptance<br />
May 11th, 2018 Camera-ready Due<br />
July 15th, 2018 Tutorials<br />
July 16th–18th, 2018 Main Conference<br />
July 19th–20th, 2018 Tutorials and Workshops<br />
<br />
We have already announced two invited speakers:<br />
Carolyn Penstein Rose, Language Technologies Institute at Carnegie Mellon University, USA<br />
Anton van den Hengel, Australian Centre for Visual Technologies at University of Adelaide, Australia<br />
<br />
In a cooperation with NAACL 2018 Program Chairs, we implemented a structured review form that should guide reviewers to better assess strengths and weaknesses of the submissions as well as to help the area chairs in their acceptance/rejection decisions. The form has been made publicly available ( http://acl2018.org/2018/02/20/sample-review-form/ ).<br />
<br />
Summary of upcoming tasks<br />
Finish area re-assignments and desk rejects<br />
Initiate the review process<br />
Publish statistics on submissions<br />
Initiate Author response period<br />
Collect decisions from ACs<br />
Elicit meta-reviews<br />
Decide border cases<br />
Publish notification of acceptance<br />
Update financial picture<br />
Integrate TACL papers<br />
Collect camera ready submissions<br />
Create the conference program<br />
Recruit session chairs<br />
Compile statistics for ACL wiki + business meeting<br />
Compile report<br />
Publish updates on the ACL web site</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2018Q1_Reports:_ACL_2018&diff=723722018Q1 Reports: ACL 20182018-03-01T12:21:07Z<p>JoakimNivre: Created page with "== '''General Chair''' == Claire Cardie, Cornell University The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne,..."</p>
<hr />
<div>== '''General Chair''' ==<br />
Claire Cardie, Cornell University<br />
<br />
The 56th annual meeting of the Association for Computational Linguistics (ACL 2018) will take place in Melbourne, Australia at the Melbourne Convention and Exhibition Centre July 15th-20th, 2018. I believe that we have an excellent team for putting together the conference. For the organizing positions that I had primary control over (Workshops, Tutorials, Demos, Publications, Student Research Workshop), I attempted to recruit an even number of women and men. Among these, there are 7 female organizers (not including me) and 8 male organizers.<br />
<br />
We have been using Slack for most intra-committee communication, and especially for requests to the Webmaster. <br />
<br />
This report is structured around the activities associated with each Chair position, each with a separate section below.<br />
<br />
<br />
'''Aravind Joshi tribute:''' In addition to what is reported below, I am hoping that we can incorporate some kind of tribute to Aravind Joshi and am working with the Local Arrangements and Program Chairs to determine what would be best. One option would involve making use of about 30 minutes of an interview that Joel Tetrault and Ellie Pavlick did with Aravind in 2016 (as part of a funny video they did to introduce the Poster Madness session of NAACL 2016 (https://www.youtube.com/watch?v=vQxQ25x24nw)). According to Joel,<br />
<br />
“...I have a lot of unused footage from that interview - maybe 30+ minutes. At a certain point I just started asking him random questions about what he likes, his past, etc. I'll have to make sure I still have it (switched computers) but pretty sure I do. If this seems like it could be nice/fun to include as a memoriam, just let me know and I can find it and clean it up.” <br />
<br />
The idea would be to run this video --- either as part of a plenary session or continuously at a location where people could view it at their leisure. Getting feedback on this from the Executive Committee would be great!</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Fellows_Program&diff=72334Fellows Program2018-02-27T15:46:32Z<p>JoakimNivre: /* Procedure for Selecting New Fellows */</p>
<hr />
<div>== ACL Fellows Program ==<br />
<br />
The ACL Fellows program intends to recognize individuals who have made outstanding contributions to the association or to the field of computational linguistics in general. The program was created in 2011 and the selection criteria and rules for nomination and selection were last revised in 2017.<br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
=== Selection Criteria for Fellows ===<br />
<br />
A person shall be qualified as a candidate for being ACL Fellow if the candidate has made significant contributions in areas including but not limited to the following:<br />
<br />
# Scientific and technical excellence: Important technical contributions to computational linguistics. This should be interpreted in a broad sense to include research and technical development, contributions to academic, government or industrial group efforts, and release of software and resources. Evidence of technical contributions is typically in the form of technical results, publications, patents, and awards but other relevant forms of evidence should be considered as well. <br />
# Service excellence: Extended service to the ACL or other scientific organizations whose mission aligns with that of the ACL. This includes being a member of a board or executive committee, being the editor of a journal, serving in major conference chair positions, or doing other voluntary work of significance for the organization. <br />
# Enabling excellence: Significant educational and outreach activities with broader impact. This includes contributions to improve the visibility and impact of computational linguistics in society as a whole, such as the development and promotion of educational programs, raising awareness of equity and diversity issues, building bridges between academia and industry, or collaborating with government agencies and other pro-societal organizations.<br />
<br />
Qualified candidates are furthermore expected to observe accepted professional and ethical standards both within and outside their scientific activities. <br />
<br />
=== Procedure for Selecting New Fellows ===<br />
<br />
# Nominations for new Fellows can be made by any current ACL member and need to be supported by recommendations from two additional ACL members. '''Note:''' Members of the nominating committee are not allowed to contribute to new nominations (as nominators or recommenders) while serving on the committee.<br />
# To be eligible, the nominee must have been a member of the ACL for 3 out of the last 5 calendar years, including the year when they are nominated. '''Note:''' Members of the Executive Committee and the Nominating Committee are not eligible to become Fellows while serving.<br />
# Nominations and supporting recommendations must be submitted using the special form available [https://www.aclweb.org/portal/acl-fellows here].<br />
# The deadline for nominations each year is October 1.<br />
# The selection of new fellows from the pool of nominees is handled by the ACL Nominating Committee, consisting of three past ACL presidents and six ACL Fellows. <br />
# The committee is charged with soliciting a large and diverse pool of candidates and with making the final selection in accordance with the criteria stated above.<br />
# The selection of the committee will be submitted for formal approval to the ACL Executive Committee, providing whatever explanations and supporting documentation the Executive Committee requires.<br />
# The role of the Executive is to ensure consistency and clarity in the decision process, and they should not overrule the committee’s proposal or advance alternative candidates. <br />
# The number of new fellows appointed in a year should not represent more than 0.2% of the current ACL membership.<br />
# Nominators should be informed about the outcome of their nominations but without specific information about why a particular nominee was not elected.<br />
<br />
=== ACL Nominating Committee === <br />
<br />
The selection of new fellows is handled by the ACL Nominating Committee, based on nominations from ACL members. The membership recently amended the [[ACL_Constitution]] to designate the makeup of the Nominating Committee as follows: <br />
<br />
:There shall be a Nominating Committee consisting of the three most recent Past Presidents, each serving for the three years following their own Presidency, and six ACL Fellows selected subject to diversity requirements set forth by the Executive. <br />
<br />
The current members of the Nominating Committee (as of January 2018) are:<br />
<br />
Six existing Fellows:<br />
* Michael Collins (male, Americas) (2017-2018) (was Exec nominations subchair of 2017)<br />
* Eva Hajicová (female, EMEA) (2017-2018) (LTA nomination subchair of 2018)<br />
* Julia Hirschberg (female, Americas) (2017-2019) (Fellows selection subchair of 2018)<br />
* Yuji Matsumoto (male, APAC) (2017-2019) (Exec nominations subchair of 2018)<br />
* Eduard Hovy (male, Americas) (2018-2020)<br />
* Candace Sidner (female, Americas) (2018-2020)<br />
<br />
Three ACL past presidents:<br />
* Chris Manning (male, Americas) (2017-2018) (General Chair of the committee)<br />
* Pushpak Bhattacharyya (male, APAC) (2017-2019)<br />
* Joakim Nivre (male, EMEA) (2018-2020)</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Fellows_Program&diff=72333Fellows Program2018-02-27T15:42:24Z<p>JoakimNivre: /* Procedure for Selecting New Fellows */</p>
<hr />
<div>== ACL Fellows Program ==<br />
<br />
The ACL Fellows program intends to recognize individuals who have made outstanding contributions to the association or to the field of computational linguistics in general. The program was created in 2011 and the selection criteria and rules for nomination and selection were last revised in 2017.<br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
=== Selection Criteria for Fellows ===<br />
<br />
A person shall be qualified as a candidate for being ACL Fellow if the candidate has made significant contributions in areas including but not limited to the following:<br />
<br />
# Scientific and technical excellence: Important technical contributions to computational linguistics. This should be interpreted in a broad sense to include research and technical development, contributions to academic, government or industrial group efforts, and release of software and resources. Evidence of technical contributions is typically in the form of technical results, publications, patents, and awards but other relevant forms of evidence should be considered as well. <br />
# Service excellence: Extended service to the ACL or other scientific organizations whose mission aligns with that of the ACL. This includes being a member of a board or executive committee, being the editor of a journal, serving in major conference chair positions, or doing other voluntary work of significance for the organization. <br />
# Enabling excellence: Significant educational and outreach activities with broader impact. This includes contributions to improve the visibility and impact of computational linguistics in society as a whole, such as the development and promotion of educational programs, raising awareness of equity and diversity issues, building bridges between academia and industry, or collaborating with government agencies and other pro-societal organizations.<br />
<br />
Qualified candidates are furthermore expected to observe accepted professional and ethical standards both within and outside their scientific activities. <br />
<br />
=== Procedure for Selecting New Fellows ===<br />
<br />
# Nominations for new Fellows can be made by any current ACL member and need to be supported by recommendations from two additional ACL members. '''Note:''' Members of the nominating committee are not allowed to contribute to new nominations (as nominators or recommenders) while serving on the committee.<br />
# To be eligible, the nominee must have been a member of the ACL for 3 out of the last 5 calendar years, including the year when they are nominated. '''Note:''' Members of the Executive Committee and the Nominating Committee are not eligible to become Fellows while serving.<br />
# Nominations and supporting recommendations must be submitted using the special form available [https://www.aclweb.org/portal/acl-fellows here].<br />
# The deadline for nominations each year is October 1.<br />
# The selection of new fellows from the pool of nominees is handled by the ACL Nominating Committee, consisting of three past ACL presidents and six ACL Fellows. <br />
# The committee is charged with soliciting a large and diverse pool of candidates and with making the final selection in accordance with the criteria stated above.<br />
# The selection of the committee will be submitted for formal approval to the ACL Executive Committee, providing whatever explanations and supporting documentation the Executive Committee requires.<br />
# The role of the Executive is to ensure consistency and clarity in the decision process, and they should not overrule the committee’s proposal or advance alternative candidates. <br />
# The number of new fellows appointed in a year should not represent more than 0.2% of the current ACL membership.<br />
<br />
=== ACL Nominating Committee === <br />
<br />
The selection of new fellows is handled by the ACL Nominating Committee, based on nominations from ACL members. The membership recently amended the [[ACL_Constitution]] to designate the makeup of the Nominating Committee as follows: <br />
<br />
:There shall be a Nominating Committee consisting of the three most recent Past Presidents, each serving for the three years following their own Presidency, and six ACL Fellows selected subject to diversity requirements set forth by the Executive. <br />
<br />
The current members of the Nominating Committee (as of January 2018) are:<br />
<br />
Six existing Fellows:<br />
* Michael Collins (male, Americas) (2017-2018) (was Exec nominations subchair of 2017)<br />
* Eva Hajicová (female, EMEA) (2017-2018) (LTA nomination subchair of 2018)<br />
* Julia Hirschberg (female, Americas) (2017-2019) (Fellows selection subchair of 2018)<br />
* Yuji Matsumoto (male, APAC) (2017-2019) (Exec nominations subchair of 2018)<br />
* Eduard Hovy (male, Americas) (2018-2020)<br />
* Candace Sidner (female, Americas) (2018-2020)<br />
<br />
Three ACL past presidents:<br />
* Chris Manning (male, Americas) (2017-2018) (General Chair of the committee)<br />
* Pushpak Bhattacharyya (male, APAC) (2017-2019)<br />
* Joakim Nivre (male, EMEA) (2018-2020)</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Fellows_Program&diff=72332Fellows Program2018-02-27T14:59:52Z<p>JoakimNivre: /* Procedure for Selecting New Fellows */</p>
<hr />
<div>== ACL Fellows Program ==<br />
<br />
The ACL Fellows program intends to recognize individuals who have made outstanding contributions to the association or to the field of computational linguistics in general. The program was created in 2011 and the selection criteria and rules for nomination and selection were last revised in 2017.<br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
=== Selection Criteria for Fellows ===<br />
<br />
A person shall be qualified as a candidate for being ACL Fellow if the candidate has made significant contributions in areas including but not limited to the following:<br />
<br />
# Scientific and technical excellence: Important technical contributions to computational linguistics. This should be interpreted in a broad sense to include research and technical development, contributions to academic, government or industrial group efforts, and release of software and resources. Evidence of technical contributions is typically in the form of technical results, publications, patents, and awards but other relevant forms of evidence should be considered as well. <br />
# Service excellence: Extended service to the ACL or other scientific organizations whose mission aligns with that of the ACL. This includes being a member of a board or executive committee, being the editor of a journal, serving in major conference chair positions, or doing other voluntary work of significance for the organization. <br />
# Enabling excellence: Significant educational and outreach activities with broader impact. This includes contributions to improve the visibility and impact of computational linguistics in society as a whole, such as the development and promotion of educational programs, raising awareness of equity and diversity issues, building bridges between academia and industry, or collaborating with government agencies and other pro-societal organizations.<br />
<br />
Qualified candidates are furthermore expected to observe accepted professional and ethical standards both within and outside their scientific activities. <br />
<br />
=== Procedure for Selecting New Fellows ===<br />
<br />
# Nominations for new Fellows can be made by any current ACL member and need to be supported by recommendations from two additional ACL members. '''Exception:''' Members of the nominating committee are not allowed to contribute to new nominations (as nominators or recommenders) while serving on the committee.<br />
# To be eligible, the nominee must have been a member of the ACL for 3 out of the last 5 calendar years, including the year when they are nominated, and must not be members of the Exec or the Nominating Committee at the time of nomination.<br />
# Nominations and supporting recommendations must be submitted using the special form available [https://www.aclweb.org/portal/acl-fellows here].<br />
# The deadline for nominations each year is October 1.<br />
# The selection of new fellows from the pool of nominees is handled by the ACL Nominating Committee, consisting of three past ACL presidents and six ACL Fellows. <br />
# The committee is charged with soliciting a large and diverse pool of candidates and with making the final selection in accordance with the criteria stated above.<br />
# The selection of the committee will be submitted for formal approval to the ACL executive, providing whatever explanations and supporting documentation the Executive requires.<br />
# The role of the Executive is to ensure consistency and clarity in the decision process, and they should not overrule the committee’s proposal or advance alternative candidates. <br />
# The number of new fellows appointed in a year should not represent more than 0.2% of the current ACL membership.<br />
# Members of the Exec and the Nominating Committee are not be eligible to become Fellows while serving. People should be informed about this before being nominated to the Exec.<br />
# Nominators should be informed about the outcome of their nominations but without specific information about why a particular nominee was not elected.<br />
# Information about criteria and conditions for selection (including the 0.2% rule) should be provided in the instructions for nominators.<br />
<br />
=== ACL Nominating Committee === <br />
<br />
The selection of new fellows is handled by the ACL Nominating Committee, based on nominations from ACL members. The membership recently amended the [[ACL_Constitution]] to designate the makeup of the Nominating Committee as follows: <br />
<br />
:There shall be a Nominating Committee consisting of the three most recent Past Presidents, each serving for the three years following their own Presidency, and six ACL Fellows selected subject to diversity requirements set forth by the Executive. <br />
<br />
The current members of the Nominating Committee (as of January 2018) are:<br />
<br />
Six existing Fellows:<br />
* Michael Collins (male, Americas) (2017-2018) (was Exec nominations subchair of 2017)<br />
* Eva Hajicová (female, EMEA) (2017-2018) (LTA nomination subchair of 2018)<br />
* Julia Hirschberg (female, Americas) (2017-2019) (Fellows selection subchair of 2018)<br />
* Yuji Matsumoto (male, APAC) (2017-2019) (Exec nominations subchair of 2018)<br />
* Eduard Hovy (male, Americas) (2018-2020)<br />
* Candace Sidner (female, Americas) (2018-2020)<br />
<br />
Three ACL past presidents:<br />
* Chris Manning (male, Americas) (2017-2018) (General Chair of the committee)<br />
* Pushpak Bhattacharyya (male, APAC) (2017-2019)<br />
* Joakim Nivre (male, EMEA) (2018-2020)</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Fellows_Program&diff=72331Fellows Program2018-02-27T14:56:15Z<p>JoakimNivre: /* Procedure for Selecting New Fellows */</p>
<hr />
<div>== ACL Fellows Program ==<br />
<br />
The ACL Fellows program intends to recognize individuals who have made outstanding contributions to the association or to the field of computational linguistics in general. The program was created in 2011 and the selection criteria and rules for nomination and selection were last revised in 2017.<br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
=== Selection Criteria for Fellows ===<br />
<br />
A person shall be qualified as a candidate for being ACL Fellow if the candidate has made significant contributions in areas including but not limited to the following:<br />
<br />
# Scientific and technical excellence: Important technical contributions to computational linguistics. This should be interpreted in a broad sense to include research and technical development, contributions to academic, government or industrial group efforts, and release of software and resources. Evidence of technical contributions is typically in the form of technical results, publications, patents, and awards but other relevant forms of evidence should be considered as well. <br />
# Service excellence: Extended service to the ACL or other scientific organizations whose mission aligns with that of the ACL. This includes being a member of a board or executive committee, being the editor of a journal, serving in major conference chair positions, or doing other voluntary work of significance for the organization. <br />
# Enabling excellence: Significant educational and outreach activities with broader impact. This includes contributions to improve the visibility and impact of computational linguistics in society as a whole, such as the development and promotion of educational programs, raising awareness of equity and diversity issues, building bridges between academia and industry, or collaborating with government agencies and other pro-societal organizations.<br />
<br />
Qualified candidates are furthermore expected to observe accepted professional and ethical standards both within and outside their scientific activities. <br />
<br />
=== Procedure for Selecting New Fellows ===<br />
<br />
# Nominations for new Fellows can be made by any current ACL member and need to be supported by recommendations from two additional ACL members. '''Exception:''' Members of the nominating committee are not allowed to contribute to new nominations (as nominators or recommenders) while serving on the committee.<br />
# Nominations and supporting recommendations must be submitted using the special form available [https://www.aclweb.org/portal/acl-fellows here].<br />
# The deadline for nominations each year is October 1.<br />
# The selection of new fellows from the pool of nominees is handled by the ACL Nominating Committee, consisting of three past ACL presidents and six ACL Fellows. <br />
# The committee is charged with soliciting a large and diverse pool of candidates and with making the final selection in accordance with the criteria stated above.<br />
# The selection of the committee will be submitted for formal approval to the ACL executive, providing whatever explanations and supporting documentation the Executive requires.<br />
# The role of the Executive is to ensure consistency and clarity in the decision process, and they should not overrule the committee’s proposal or advance alternative candidates. <br />
# The number of new fellows appointed in a year should not represent more than 0.2% of the current ACL membership.<br />
# Members of the Exec and the Nominating Committee are not be eligible to become Fellows while serving. People should be informed about this before being nominated to the Exec.<br />
# Nominators should be informed about the outcome of their nominations but without specific information about why a particular nominee was not elected.<br />
# Information about criteria and conditions for selection (including the 0.2% rule) should be provided in the instructions for nominators.<br />
<br />
=== ACL Nominating Committee === <br />
<br />
The selection of new fellows is handled by the ACL Nominating Committee, based on nominations from ACL members. The membership recently amended the [[ACL_Constitution]] to designate the makeup of the Nominating Committee as follows: <br />
<br />
:There shall be a Nominating Committee consisting of the three most recent Past Presidents, each serving for the three years following their own Presidency, and six ACL Fellows selected subject to diversity requirements set forth by the Executive. <br />
<br />
The current members of the Nominating Committee (as of January 2018) are:<br />
<br />
Six existing Fellows:<br />
* Michael Collins (male, Americas) (2017-2018) (was Exec nominations subchair of 2017)<br />
* Eva Hajicová (female, EMEA) (2017-2018) (LTA nomination subchair of 2018)<br />
* Julia Hirschberg (female, Americas) (2017-2019) (Fellows selection subchair of 2018)<br />
* Yuji Matsumoto (male, APAC) (2017-2019) (Exec nominations subchair of 2018)<br />
* Eduard Hovy (male, Americas) (2018-2020)<br />
* Candace Sidner (female, Americas) (2018-2020)<br />
<br />
Three ACL past presidents:<br />
* Chris Manning (male, Americas) (2017-2018) (General Chair of the committee)<br />
* Pushpak Bhattacharyya (male, APAC) (2017-2019)<br />
* Joakim Nivre (male, EMEA) (2018-2020)</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Fellows_Program&diff=72178Fellows Program2017-09-25T09:37:31Z<p>JoakimNivre: </p>
<hr />
<div>== ACL Fellows Program ==<br />
<br />
The ACL Fellows program intends to recognize individuals who have made outstanding contributions to the association or to the field of computational linguistics in general. The program was created in 2011 and the selection criteria and rules for nomination and selection were last revised in 2017.<br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
=== Selection Criteria for Fellows ===<br />
<br />
A person shall be qualified as a candidate for being ACL Fellow if the candidate has made significant contributions in areas including but not limited to the following:<br />
<br />
# Scientific and technical excellence: Important technical contributions to computational linguistics. This should be interpreted in a broad sense to include research and technical development, contributions to academic, government or industrial group efforts, and release of software and resources. Evidence of technical contributions is typically in the form of technical results, publications, patents, and awards but other relevant forms of evidence should be considered as well. <br />
# Service excellence: Extended service to the ACL or other scientific organizations whose mission aligns with that of the ACL. This includes being a member of a board or executive committee, being the editor of a journal, serving in major conference chair positions, or doing other voluntary work of significance for the organization. <br />
# Enabling excellence: Significant educational and outreach activities with broader impact. This includes contributions to improve the visibility and impact of computational linguistics in society as a whole, such as the development and promotion of educational programs, raising awareness of equity and diversity issues, building bridges between academia and industry, or collaborating with government agencies and other pro-societal organizations.<br />
<br />
Qualified candidates are furthermore expected to observe accepted professional and ethical standards both within and outside their scientific activities. <br />
<br />
=== Procedure for Selecting New Fellows ===<br />
<br />
# Nominations for new Fellows can be made by any current ACL member and need to be supported by recommendations from two additional ACL members.<br />
# To be eligible, the nominee must have been a member of the ACL for 3 out of the last 5 calendar years, including the year when they are nominated.<br />
# Nominations and supporting recommendations must be submitted using the special form available [https://www.aclweb.org/portal/acl-fellows here].<br />
# The deadline for nominations each year is October 1.<br />
# The selection of new fellows from the pool of nominees is handled by the ACL Nominating Committee, consisting of three past ACL presidents and six ACL Fellows. <br />
# The committee is charged with soliciting a large and diverse pool of candidates and with making the final selection in accordance with the criteria stated above.<br />
# The selection of the committee will be submitted for formal approval to the ACL executive, providing whatever explanations and supporting documentation the Executive requires.<br />
# The role of the Executive is to ensure consistency and clarity in the decision process, and they should not overrule the committee’s proposal or advance alternative candidates. <br />
# The number of new fellows appointed in a year should not represent more than 0.2% of the current ACL membership.<br />
<br />
=== ACL Nominating Committee === <br />
<br />
The selection of new fellows is handled by the ACL Nominating Committee, based on nominations from ACL members. The membership recently amended the [[ACL_Constitution]] to designate the makeup of the Nominating Committee as follows: <br />
<br />
:There shall be a Nominating Committee consisting of the three most recent Past Presidents, each serving for the three years following their own Presidency, and six ACL Fellows selected subject to diversity requirements set forth by the Executive. <br />
<br />
The current members of the Nominating Committee (as of January 2017) are:<br />
<br />
*Pushpak Bhattacharyya<br />
*Nicoletta Calzolari (Fellows Chair)<br />
*Eugene Charniak (LTA Chair)<br />
*Michael Collins (Exec Chair)<br />
*Eva Hajicova<br />
*Julia Hirschberg<br />
*Christopher Manning<br />
*Yuji Matsumoto<br />
*Gertjan van Noord (General Chair)</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Fellows_Program&diff=72159Fellows Program2017-08-19T15:38:35Z<p>JoakimNivre: /* Procedure for Selecting New Fellows */</p>
<hr />
<div>== ACL Fellows Program ==<br />
<br />
The ACL Fellows program intends to recognize individuals who have made outstanding contributions to the association or to the field of computational linguistics in general. The program was created in 2011 and the selection criteria and rules for nomination and selection were last revised in 2017.<br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
=== Selection Criteria for Fellows ===<br />
<br />
A person shall be qualified as a candidate for being ACL Fellow if the candidate has made significant contributions in areas including but not limited to the following:<br />
<br />
# Scientific and technical excellence: Important technical contributions to computational linguistics. This should be interpreted in a broad sense to include research and technical development, contributions to academic, government or industrial group efforts, and release of software and resources. Evidence of technical contributions is typically in the form of technical results, publications, patents, and awards but other relevant forms of evidence should be considered as well. <br />
# Service excellence: Extended service to the ACL or other scientific organizations whose mission aligns with that of the ACL. This includes being a member of a board or executive committee, being the editor of a journal, serving in major conference chair positions, or doing other voluntary work of significance for the organization. <br />
# Enabling excellence: Significant educational and outreach activities with broader impact. This includes contributions to improve the visibility and impact of computational linguistics in society as a whole, such as the development and promotion of educational programs, raising awareness of equity and diversity issues, building bridges between academia and industry, or collaborating with government agencies and other pro-societal organizations.<br />
<br />
Qualified candidates are furthermore expected to observe accepted professional and ethical standards both within and outside their scientific activities. <br />
<br />
=== Procedure for Selecting New Fellows ===<br />
<br />
# Nominations for new Fellows can be made by any current ACL member and need to be supported by recommendations from two additional ACL members.<br />
# To be eligible, the nominee must have been a member of the ACL for 3 out of the last 5 calendar years, including the year when they are nominated.<br />
# Nominations and supporting recommendations must be submitted using the special form available [https://www.aclweb.org/portal/acl-fellows here].<br />
# The deadline for nominations each year is October 1.<br />
# The selection of new fellows from the pool of nominees is handled by the ACL Nominating Committee, consisting of three past ACL presidents and six ACL Fellows. <br />
# The committee is charged with soliciting a large and diverse pool of candidates and with making the final selection in accordance with the criteria stated above.<br />
# The selection of the committee will be submitted for formal approval to the ACL executive, providing whatever explanations and supporting documentation the Executive requires.<br />
# The role of the Executive is to ensure consistency and clarity in the decision process, and they should not overrule the committee’s proposal or advance alternative candidates. <br />
# The number of new fellows appointed in a year should not represent more than 0.2% of the current ACL membership.<br />
<br />
=== ACL Nominating Committee === <br />
<br />
The selection of new fellows is handled by the ACL Nominating Committee, based on nominations from ACL members. The membership recently amended the [[ACL_Constitution]] to designate the makeup of the Nominating Committee as follows: <br />
<br />
:There shall be a Nominating Committee consisting of the three most recent Past Presidents, each serving for the three years following their own Presidency, and six ACL Fellows selected subject to diversity requirements set forth by the Executive. <br />
<br />
The current members of the Nominating Committee (as of January 2017) are:<br />
<br />
*Pushpak Bhattacharyya<br />
*Nicoletta Calzolari<br />
*Eugene Charniak (LTA Chair)<br />
*Michael Collins (Exec Chair)<br />
*Eva Hajicova<br />
*Julia Hirschberg (Fellows Chair)<br />
*Christopher Manning<br />
*Yuji Matsumoto<br />
*Gertjan van Noord (General Chair)</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Fellows_Program&diff=72158Fellows Program2017-08-19T15:38:12Z<p>JoakimNivre: /* Procedure for Selecting New Fellows */</p>
<hr />
<div>== ACL Fellows Program ==<br />
<br />
The ACL Fellows program intends to recognize individuals who have made outstanding contributions to the association or to the field of computational linguistics in general. The program was created in 2011 and the selection criteria and rules for nomination and selection were last revised in 2017.<br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
=== Selection Criteria for Fellows ===<br />
<br />
A person shall be qualified as a candidate for being ACL Fellow if the candidate has made significant contributions in areas including but not limited to the following:<br />
<br />
# Scientific and technical excellence: Important technical contributions to computational linguistics. This should be interpreted in a broad sense to include research and technical development, contributions to academic, government or industrial group efforts, and release of software and resources. Evidence of technical contributions is typically in the form of technical results, publications, patents, and awards but other relevant forms of evidence should be considered as well. <br />
# Service excellence: Extended service to the ACL or other scientific organizations whose mission aligns with that of the ACL. This includes being a member of a board or executive committee, being the editor of a journal, serving in major conference chair positions, or doing other voluntary work of significance for the organization. <br />
# Enabling excellence: Significant educational and outreach activities with broader impact. This includes contributions to improve the visibility and impact of computational linguistics in society as a whole, such as the development and promotion of educational programs, raising awareness of equity and diversity issues, building bridges between academia and industry, or collaborating with government agencies and other pro-societal organizations.<br />
<br />
Qualified candidates are furthermore expected to observe accepted professional and ethical standards both within and outside their scientific activities. <br />
<br />
=== Procedure for Selecting New Fellows ===<br />
<br />
# Nominations for new Fellows can be made by any current ACL member and need to be supported by recommendations from two additional ACL members.<br />
# To be eligible, the nominee must have been a member of the ACL for 3 out of the last 5 calendar years, including the year when they are nominated.<br />
# Nominations and supporting recommendations must be submitted using the special form available [here https://www.aclweb.org/portal/acl-fellows].<br />
# The deadline for nominations each year is October 1.<br />
# The selection of new fellows from the pool of nominees is handled by the ACL Nominating Committee, consisting of three past ACL presidents and six ACL Fellows. <br />
# The committee is charged with soliciting a large and diverse pool of candidates and with making the final selection in accordance with the criteria stated above.<br />
# The selection of the committee will be submitted for formal approval to the ACL executive, providing whatever explanations and supporting documentation the Executive requires.<br />
# The role of the Executive is to ensure consistency and clarity in the decision process, and they should not overrule the committee’s proposal or advance alternative candidates. <br />
# The number of new fellows appointed in a year should not represent more than 0.2% of the current ACL membership.<br />
<br />
=== ACL Nominating Committee === <br />
<br />
The selection of new fellows is handled by the ACL Nominating Committee, based on nominations from ACL members. The membership recently amended the [[ACL_Constitution]] to designate the makeup of the Nominating Committee as follows: <br />
<br />
:There shall be a Nominating Committee consisting of the three most recent Past Presidents, each serving for the three years following their own Presidency, and six ACL Fellows selected subject to diversity requirements set forth by the Executive. <br />
<br />
The current members of the Nominating Committee (as of January 2017) are:<br />
<br />
*Pushpak Bhattacharyya<br />
*Nicoletta Calzolari<br />
*Eugene Charniak (LTA Chair)<br />
*Michael Collins (Exec Chair)<br />
*Eva Hajicova<br />
*Julia Hirschberg (Fellows Chair)<br />
*Christopher Manning<br />
*Yuji Matsumoto<br />
*Gertjan van Noord (General Chair)</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Fellows_Program&diff=72157Fellows Program2017-08-19T15:36:50Z<p>JoakimNivre: /* Procedure for Selecting New Fellows */</p>
<hr />
<div>== ACL Fellows Program ==<br />
<br />
The ACL Fellows program intends to recognize individuals who have made outstanding contributions to the association or to the field of computational linguistics in general. The program was created in 2011 and the selection criteria and rules for nomination and selection were last revised in 2017.<br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
=== Selection Criteria for Fellows ===<br />
<br />
A person shall be qualified as a candidate for being ACL Fellow if the candidate has made significant contributions in areas including but not limited to the following:<br />
<br />
# Scientific and technical excellence: Important technical contributions to computational linguistics. This should be interpreted in a broad sense to include research and technical development, contributions to academic, government or industrial group efforts, and release of software and resources. Evidence of technical contributions is typically in the form of technical results, publications, patents, and awards but other relevant forms of evidence should be considered as well. <br />
# Service excellence: Extended service to the ACL or other scientific organizations whose mission aligns with that of the ACL. This includes being a member of a board or executive committee, being the editor of a journal, serving in major conference chair positions, or doing other voluntary work of significance for the organization. <br />
# Enabling excellence: Significant educational and outreach activities with broader impact. This includes contributions to improve the visibility and impact of computational linguistics in society as a whole, such as the development and promotion of educational programs, raising awareness of equity and diversity issues, building bridges between academia and industry, or collaborating with government agencies and other pro-societal organizations.<br />
<br />
Qualified candidates are furthermore expected to observe accepted professional and ethical standards both within and outside their scientific activities. <br />
<br />
=== Procedure for Selecting New Fellows ===<br />
<br />
# Nominations for new Fellows can be made by any current ACL member and need to be supported by recommendations from two additional ACL members.<br />
# To be eligible, the nominee must have been a member of the ACL for 3 out of the last 5 calendar years, including the year when they are nominated.<br />
# Nominations and supporting recommendations must be submitted using the special form available at [https://www.aclweb.org/portal/acl-fellows].<br />
# The deadline for nominations each year is October 1.<br />
# The selection of new fellows from the pool of nominees is handled by the ACL Nominating Committee, consisting of three past ACL presidents and six ACL Fellows. <br />
# The committee is charged with soliciting a large and diverse pool of candidates and with making the final selection in accordance with the criteria stated above.<br />
# The selection of the committee will be submitted for formal approval to the ACL executive, providing whatever explanations and supporting documentation the Executive requires.<br />
# The role of the Executive is to ensure consistency and clarity in the decision process, and they should not overrule the committee’s proposal or advance alternative candidates. <br />
# The number of new fellows appointed in a year should not represent more than 0.2% of the current ACL membership.<br />
<br />
=== ACL Nominating Committee === <br />
<br />
The selection of new fellows is handled by the ACL Nominating Committee, based on nominations from ACL members. The membership recently amended the [[ACL_Constitution]] to designate the makeup of the Nominating Committee as follows: <br />
<br />
:There shall be a Nominating Committee consisting of the three most recent Past Presidents, each serving for the three years following their own Presidency, and six ACL Fellows selected subject to diversity requirements set forth by the Executive. <br />
<br />
The current members of the Nominating Committee (as of January 2017) are:<br />
<br />
*Pushpak Bhattacharyya<br />
*Nicoletta Calzolari<br />
*Eugene Charniak (LTA Chair)<br />
*Michael Collins (Exec Chair)<br />
*Eva Hajicova<br />
*Julia Hirschberg (Fellows Chair)<br />
*Christopher Manning<br />
*Yuji Matsumoto<br />
*Gertjan van Noord (General Chair)</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Fellows_Program&diff=72156Fellows Program2017-08-19T15:35:41Z<p>JoakimNivre: /* ACL Nominating Committee */</p>
<hr />
<div>== ACL Fellows Program ==<br />
<br />
The ACL Fellows program intends to recognize individuals who have made outstanding contributions to the association or to the field of computational linguistics in general. The program was created in 2011 and the selection criteria and rules for nomination and selection were last revised in 2017.<br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
=== Selection Criteria for Fellows ===<br />
<br />
A person shall be qualified as a candidate for being ACL Fellow if the candidate has made significant contributions in areas including but not limited to the following:<br />
<br />
# Scientific and technical excellence: Important technical contributions to computational linguistics. This should be interpreted in a broad sense to include research and technical development, contributions to academic, government or industrial group efforts, and release of software and resources. Evidence of technical contributions is typically in the form of technical results, publications, patents, and awards but other relevant forms of evidence should be considered as well. <br />
# Service excellence: Extended service to the ACL or other scientific organizations whose mission aligns with that of the ACL. This includes being a member of a board or executive committee, being the editor of a journal, serving in major conference chair positions, or doing other voluntary work of significance for the organization. <br />
# Enabling excellence: Significant educational and outreach activities with broader impact. This includes contributions to improve the visibility and impact of computational linguistics in society as a whole, such as the development and promotion of educational programs, raising awareness of equity and diversity issues, building bridges between academia and industry, or collaborating with government agencies and other pro-societal organizations.<br />
<br />
Qualified candidates are furthermore expected to observe accepted professional and ethical standards both within and outside their scientific activities. <br />
<br />
=== Procedure for Selecting New Fellows ===<br />
<br />
# Nominations for new Fellows can be made by any current ACL member and need to be supported by recommendations from two additional ACL members.<br />
# To be eligible, the nominee must have been a member of the ACL for 3 out of the last 5 calendar years, including the year when they are nominated.<br />
# Nominations and supporting recommendations must be submitted using the special form available at <link coming soon>.<br />
# The deadline for nominations each year is October 1.<br />
# The selection of new fellows from the pool of nominees is handled by the ACL Nominating Committee, consisting of three past ACL presidents and six ACL Fellows. <br />
# The committee is charged with soliciting a large and diverse pool of candidates and with making the final selection in accordance with the criteria stated above.<br />
# The selection of the committee will be submitted for formal approval to the ACL executive, providing whatever explanations and supporting documentation the Executive requires.<br />
# The role of the Executive is to ensure consistency and clarity in the decision process, and they should not overrule the committee’s proposal or advance alternative candidates. <br />
# The number of new fellows appointed in a year should not represent more than 0.2% of the current ACL membership.<br />
<br />
=== ACL Nominating Committee === <br />
<br />
The selection of new fellows is handled by the ACL Nominating Committee, based on nominations from ACL members. The membership recently amended the [[ACL_Constitution]] to designate the makeup of the Nominating Committee as follows: <br />
<br />
:There shall be a Nominating Committee consisting of the three most recent Past Presidents, each serving for the three years following their own Presidency, and six ACL Fellows selected subject to diversity requirements set forth by the Executive. <br />
<br />
The current members of the Nominating Committee (as of January 2017) are:<br />
<br />
*Pushpak Bhattacharyya<br />
*Nicoletta Calzolari<br />
*Eugene Charniak (LTA Chair)<br />
*Michael Collins (Exec Chair)<br />
*Eva Hajicova<br />
*Julia Hirschberg (Fellows Chair)<br />
*Christopher Manning<br />
*Yuji Matsumoto<br />
*Gertjan van Noord (General Chair)</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Fellows_Program&diff=71797Fellows Program2017-06-29T16:51:03Z<p>JoakimNivre: /* Nominating Committee */</p>
<hr />
<div>== ACL Fellows Program ==<br />
<br />
The ACL Fellows program intends to recognize individuals who have made outstanding contributions to the association or to the field of computational linguistics in general. The program was created in 2011 and the selection criteria and rules for nomination and selection were last revised in 2017.<br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
=== Selection Criteria for Fellows ===<br />
<br />
A person shall be qualified as a candidate for being ACL Fellow if the candidate has made significant contributions in areas including but not limited to the following:<br />
<br />
# Scientific and technical excellence: Important technical contributions to computational linguistics. This should be interpreted in a broad sense to include research and technical development, contributions to academic, government or industrial group efforts, and release of software and resources. Evidence of technical contributions is typically in the form of technical results, publications, patents, and awards but other relevant forms of evidence should be considered as well. <br />
# Service excellence: Extended service to the ACL or other scientific organizations whose mission aligns with that of the ACL. This includes being a member of a board or executive committee, being the editor of a journal, serving in major conference chair positions, or doing other voluntary work of significance for the organization. <br />
# Enabling excellence: Significant educational and outreach activities with broader impact. This includes contributions to improve the visibility and impact of computational linguistics in society as a whole, such as the development and promotion of educational programs, raising awareness of equity and diversity issues, building bridges between academia and industry, or collaborating with government agencies and other pro-societal organizations.<br />
<br />
Qualified candidates are furthermore expected to observe accepted professional and ethical standards both within and outside their scientific activities. <br />
<br />
=== Procedure for Selecting New Fellows ===<br />
<br />
# Nominations for new Fellows can be made by any current ACL member and need to be supported by recommendations from two additional ACL members.<br />
# To be eligible, the nominee must have been a member of the ACL for 3 out of the last 5 calendar years, including the year when they are nominated.<br />
# Nominations and supporting recommendations must be submitted using the special form available at <link coming soon>.<br />
# The deadline for nominations each year is October 1.<br />
# The selection of new fellows from the pool of nominees is handled by the ACL Nominating Committee, consisting of three past ACL presidents and six ACL Fellows. <br />
# The committee is charged with soliciting a large and diverse pool of candidates and with making the final selection in accordance with the criteria stated above.<br />
# The selection of the committee will be submitted for formal approval to the ACL executive, providing whatever explanations and supporting documentation the Executive requires.<br />
# The role of the Executive is to ensure consistency and clarity in the decision process, and they should not overrule the committee’s proposal or advance alternative candidates. <br />
# The number of new fellows appointed in a year should not represent more than 0.2% of the current ACL membership.<br />
<br />
=== ACL Nominating Committee === <br />
<br />
The selection of new fellows is handled by the ACL Nominating Committee, based on nominations from ACL members. The membership recently amended the [[ACL_Constitution]] to designate the makeup of the Nominating Committee as follows: <br />
<br />
:There shall be a Nominating Committee consisting of the three most recent Past Presidents, each serving for the three years following their own Presidency, and six ACL Fellows selected subject to diversity requirements set forth by the Executive. <br />
<br />
The current members of the Nominating Committee (as of January 2017) are:<br />
<br />
*Pushpak Bhattacharyya<br />
*Nicoletta Calzolari<br />
*Eugene Charniak<br />
*Michael Collins<br />
*Eva Hajicova<br />
*Julia Hirschberg<br />
*Christopher Manning<br />
*Yuji Matsumoto<br />
*Gertjan van Noord (chair)</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Fellows_Program&diff=71796Fellows Program2017-06-29T16:50:30Z<p>JoakimNivre: /* Fellows Nominating Committee */</p>
<hr />
<div>== ACL Fellows Program ==<br />
<br />
The ACL Fellows program intends to recognize individuals who have made outstanding contributions to the association or to the field of computational linguistics in general. The program was created in 2011 and the selection criteria and rules for nomination and selection were last revised in 2017.<br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
=== Selection Criteria for Fellows ===<br />
<br />
A person shall be qualified as a candidate for being ACL Fellow if the candidate has made significant contributions in areas including but not limited to the following:<br />
<br />
# Scientific and technical excellence: Important technical contributions to computational linguistics. This should be interpreted in a broad sense to include research and technical development, contributions to academic, government or industrial group efforts, and release of software and resources. Evidence of technical contributions is typically in the form of technical results, publications, patents, and awards but other relevant forms of evidence should be considered as well. <br />
# Service excellence: Extended service to the ACL or other scientific organizations whose mission aligns with that of the ACL. This includes being a member of a board or executive committee, being the editor of a journal, serving in major conference chair positions, or doing other voluntary work of significance for the organization. <br />
# Enabling excellence: Significant educational and outreach activities with broader impact. This includes contributions to improve the visibility and impact of computational linguistics in society as a whole, such as the development and promotion of educational programs, raising awareness of equity and diversity issues, building bridges between academia and industry, or collaborating with government agencies and other pro-societal organizations.<br />
<br />
Qualified candidates are furthermore expected to observe accepted professional and ethical standards both within and outside their scientific activities. <br />
<br />
=== Procedure for Selecting New Fellows ===<br />
<br />
# Nominations for new Fellows can be made by any current ACL member and need to be supported by recommendations from two additional ACL members.<br />
# To be eligible, the nominee must have been a member of the ACL for 3 out of the last 5 calendar years, including the year when they are nominated.<br />
# Nominations and supporting recommendations must be submitted using the special form available at <link coming soon>.<br />
# The deadline for nominations each year is October 1.<br />
# The selection of new fellows from the pool of nominees is handled by the ACL Nominating Committee, consisting of three past ACL presidents and six ACL Fellows. <br />
# The committee is charged with soliciting a large and diverse pool of candidates and with making the final selection in accordance with the criteria stated above.<br />
# The selection of the committee will be submitted for formal approval to the ACL executive, providing whatever explanations and supporting documentation the Executive requires.<br />
# The role of the Executive is to ensure consistency and clarity in the decision process, and they should not overrule the committee’s proposal or advance alternative candidates. <br />
# The number of new fellows appointed in a year should not represent more than 0.2% of the current ACL membership.<br />
<br />
=== Nominating Committee === <br />
<br />
The selection of new fellows is handled by the ACL Nominating Committee, based on nominations from ACL members. The membership recently amended the [[ACL_Constitution]] to designate the makeup of the Nominating Committee as follows: <br />
<br />
:There shall be a Nominating Committee consisting of the three most recent Past Presidents, each serving for the three years following their own Presidency, and six ACL Fellows selected subject to diversity requirements set forth by the Executive. <br />
<br />
The current members of the Nominating Committee (as of January 2017) are:<br />
<br />
*Pushpak Bhattacharyya<br />
*Nicoletta Calzolari<br />
*Eugene Charniak<br />
*Michael Collins<br />
*Eva Hajicova<br />
*Julia Hirschberg<br />
*Christopher Manning<br />
*Yuji Matsumoto<br />
*Gertjan van Noord (chair)</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Fellows_Program&diff=71795Fellows Program2017-06-29T16:48:33Z<p>JoakimNivre: </p>
<hr />
<div>== ACL Fellows Program ==<br />
<br />
The ACL Fellows program intends to recognize individuals who have made outstanding contributions to the association or to the field of computational linguistics in general. The program was created in 2011 and the selection criteria and rules for nomination and selection were last revised in 2017.<br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
=== Selection Criteria for Fellows ===<br />
<br />
A person shall be qualified as a candidate for being ACL Fellow if the candidate has made significant contributions in areas including but not limited to the following:<br />
<br />
# Scientific and technical excellence: Important technical contributions to computational linguistics. This should be interpreted in a broad sense to include research and technical development, contributions to academic, government or industrial group efforts, and release of software and resources. Evidence of technical contributions is typically in the form of technical results, publications, patents, and awards but other relevant forms of evidence should be considered as well. <br />
# Service excellence: Extended service to the ACL or other scientific organizations whose mission aligns with that of the ACL. This includes being a member of a board or executive committee, being the editor of a journal, serving in major conference chair positions, or doing other voluntary work of significance for the organization. <br />
# Enabling excellence: Significant educational and outreach activities with broader impact. This includes contributions to improve the visibility and impact of computational linguistics in society as a whole, such as the development and promotion of educational programs, raising awareness of equity and diversity issues, building bridges between academia and industry, or collaborating with government agencies and other pro-societal organizations.<br />
<br />
Qualified candidates are furthermore expected to observe accepted professional and ethical standards both within and outside their scientific activities. <br />
<br />
=== Procedure for Selecting New Fellows ===<br />
<br />
# Nominations for new Fellows can be made by any current ACL member and need to be supported by recommendations from two additional ACL members.<br />
# To be eligible, the nominee must have been a member of the ACL for 3 out of the last 5 calendar years, including the year when they are nominated.<br />
# Nominations and supporting recommendations must be submitted using the special form available at <link coming soon>.<br />
# The deadline for nominations each year is October 1.<br />
# The selection of new fellows from the pool of nominees is handled by the ACL Nominating Committee, consisting of three past ACL presidents and six ACL Fellows. <br />
# The committee is charged with soliciting a large and diverse pool of candidates and with making the final selection in accordance with the criteria stated above.<br />
# The selection of the committee will be submitted for formal approval to the ACL executive, providing whatever explanations and supporting documentation the Executive requires.<br />
# The role of the Executive is to ensure consistency and clarity in the decision process, and they should not overrule the committee’s proposal or advance alternative candidates. <br />
# The number of new fellows appointed in a year should not represent more than 0.2% of the current ACL membership.<br />
<br />
=== Fellows Nominating Committee === <br />
<br />
The membership recently amended the [[ACL_Constitution]] to designate the makeup of the Nominating Committee for the ACL Fellows as follows: <br />
<br />
:There shall be a Nominating Committee consisting of the three most recent Past Presidents, each serving for the three years following their own Presidency, and six ACL Fellows selected subject to diversity requirements set forth by the Executive. <br />
<br />
The current members of the nominating committee (as of June 21, 2017) are:<br />
<br />
*Pushpak Bhattacharyya<br />
*Nicoletta Calzolari<br />
*Eugene Charniak<br />
*Michael Collins<br />
*Eva Hajicova<br />
*Julia Hirschberg<br />
*Christopher Manning<br />
*Yuji Matsumoto<br />
*Gertjan van Noord (chair)</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2017Q3_Reports:_ACL_2018&diff=717942017Q3 Reports: ACL 20182017-06-27T10:03:24Z<p>JoakimNivre: /* Upcoming tasks */</p>
<hr />
<div>== ACL 2018 - report by Joakim Nivre ==<br />
<br />
In 2018 there will be an ACL conference in Melbourne, Australia. The conference will take place at the Melbourne Convention and Exhibition Centre, with local organisers from the University of Melbourne. The dates are: July 15-20, 2018.<br />
<br />
=== Coordinating Committee ===<br />
<br />
The conference coordinating committee is:<br />
<br />
* Joakim Nivre (chair; ACL past president in 2018) joakim.nivre@lingfil.uu.se<br />
* Shiqi Zhao (ACL secretary) zhaoshiqi.acl@gmail.com<br />
* Graeme Hirst (ACL treasurer) gh@cs.toronto.edu<br />
* Yejin Choi (ACL board) yejin@cs.washington.edu<br />
* Priscilla Rasmussen (ACL business officer) acl@aclweb.org<br />
* Pascale Fung (AFNLP representative) pascale@ece.ust.hk<br />
* Haizhou Li (AFNLP representative) hli@i2r.a-star.edu.sg<br />
* Yuji Matsumoto (AFNLP representative) matsu@is.naist.jp<br />
* Jong Park (AFNLP representative) park@cs.kaist.ac.kr<br />
<br />
Key Organizers: <br />
<br />
* Claire Cardie, general chair, <cardie@cs.cornell.edu><br />
* Iryna Gurevych, program co-chair, <gurevych@ukp.informatik.tu-darmstadt.de><br />
* Yusuke Miyao, program co-chair, <yusuke@nii.ac.jp> <br />
* Tim Baldwin, local co-chair, <tbaldwin@unimelb.edu.au><br />
* Karin Verspoor, local co-chair, <Karin.Verspoor@unimelb.edu.au><br />
* Trevor Anthony Cohn, local co-chair <t.cohn@unimelb.edu.au><br />
<br />
The committee email list address is: acl18cc@aclweb.org.<br />
<br />
=== Progress ===<br />
<br />
In the last report, we reported on the appointment of Claire Cardie as general chair for the conference, the signing of the contract with Melbourne Convention and Exhibition Centre, and the establishment of the conference website at acl2018.org. <br />
<br />
Since that report:<br />
<br />
* We are very pleased to announce that Iryna Gurevych and Yusuke Miyao has accepted our invitation to the program co-chairs for the conference.<br />
* The general chair has recruited additional conference chairs, including workshop chairs, tutorial chairs, demo chairs, publication chairs, and faculty advisors for the SRW.<br />
* The local co-chairs have appointed a publicity chair, a handbook chair, local sponsorship chairs, and an exhibits coordinator.<br />
<br />
=== Upcoming tasks ===<br />
<br />
We hope to finish these goals in the next couple of weeks to months:<br />
<br />
* Presentation and video of ACL 2018 for presentation at ACL 2017 (responsible: local co-chairs).<br />
* Set up an email address for conference chairs (responsible: general chair).<br />
* Make contact with the international sponsorship committee (responsible: local co-chairs).<br />
* Finalize program chairs' timetable of calls, paper due dates etc. (responsible: program co-chairs).<br />
<br />
After that, key tasks are:<br />
<br />
* Develop conference budget. Estimate registration dates and costs (responsible: general chair, local chairs, and Priscilla).<br />
* Create call for papers, work on finding area chairs and invited speakers (responsible: program chairs).</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2017Q3_Reports:_ACL_2018&diff=717932017Q3 Reports: ACL 20182017-06-27T10:02:58Z<p>JoakimNivre: /* Progress */</p>
<hr />
<div>== ACL 2018 - report by Joakim Nivre ==<br />
<br />
In 2018 there will be an ACL conference in Melbourne, Australia. The conference will take place at the Melbourne Convention and Exhibition Centre, with local organisers from the University of Melbourne. The dates are: July 15-20, 2018.<br />
<br />
=== Coordinating Committee ===<br />
<br />
The conference coordinating committee is:<br />
<br />
* Joakim Nivre (chair; ACL past president in 2018) joakim.nivre@lingfil.uu.se<br />
* Shiqi Zhao (ACL secretary) zhaoshiqi.acl@gmail.com<br />
* Graeme Hirst (ACL treasurer) gh@cs.toronto.edu<br />
* Yejin Choi (ACL board) yejin@cs.washington.edu<br />
* Priscilla Rasmussen (ACL business officer) acl@aclweb.org<br />
* Pascale Fung (AFNLP representative) pascale@ece.ust.hk<br />
* Haizhou Li (AFNLP representative) hli@i2r.a-star.edu.sg<br />
* Yuji Matsumoto (AFNLP representative) matsu@is.naist.jp<br />
* Jong Park (AFNLP representative) park@cs.kaist.ac.kr<br />
<br />
Key Organizers: <br />
<br />
* Claire Cardie, general chair, <cardie@cs.cornell.edu><br />
* Iryna Gurevych, program co-chair, <gurevych@ukp.informatik.tu-darmstadt.de><br />
* Yusuke Miyao, program co-chair, <yusuke@nii.ac.jp> <br />
* Tim Baldwin, local co-chair, <tbaldwin@unimelb.edu.au><br />
* Karin Verspoor, local co-chair, <Karin.Verspoor@unimelb.edu.au><br />
* Trevor Anthony Cohn, local co-chair <t.cohn@unimelb.edu.au><br />
<br />
The committee email list address is: acl18cc@aclweb.org.<br />
<br />
=== Progress ===<br />
<br />
In the last report, we reported on the appointment of Claire Cardie as general chair for the conference, the signing of the contract with Melbourne Convention and Exhibition Centre, and the establishment of the conference website at acl2018.org. <br />
<br />
Since that report:<br />
<br />
* We are very pleased to announce that Iryna Gurevych and Yusuke Miyao has accepted our invitation to the program co-chairs for the conference.<br />
* The general chair has recruited additional conference chairs, including workshop chairs, tutorial chairs, demo chairs, publication chairs, and faculty advisors for the SRW.<br />
* The local co-chairs have appointed a publicity chair, a handbook chair, local sponsorship chairs, and an exhibits coordinator.<br />
<br />
=== Upcoming tasks ===<br />
<br />
We hope to finish these goals in the next couple of weeks to months:<br />
<br />
* Presentation and video of ACL 2018 for presentation at ACL 2017 (responsible: local co-chairs).<br />
* Appointment of remaining chairs: conference handbook chair (responsible: general chair), exhibits coordinator, publicity chair (responsible: local co-chairs).<br />
* Set up an email address for conference chairs (responsible: general chair).<br />
* Make contact with ACL sponsorship committee (responsible: local co-chairs).<br />
* Finalize program chairs' timetable of calls, paper due dates etc. (responsible: program co-chairs).<br />
<br />
After that, key tasks are:<br />
<br />
* Develop conference budget. Estimate registration dates and costs (responsible: general chair, local chairs, and Priscilla).<br />
* Create call for papers, work on finding area chairs and invited speakers (responsible: program chairs).</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2017Q3_Reports:_ACL_2018&diff=717922017Q3 Reports: ACL 20182017-06-27T10:01:56Z<p>JoakimNivre: /* Progress */</p>
<hr />
<div>== ACL 2018 - report by Joakim Nivre ==<br />
<br />
In 2018 there will be an ACL conference in Melbourne, Australia. The conference will take place at the Melbourne Convention and Exhibition Centre, with local organisers from the University of Melbourne. The dates are: July 15-20, 2018.<br />
<br />
=== Coordinating Committee ===<br />
<br />
The conference coordinating committee is:<br />
<br />
* Joakim Nivre (chair; ACL past president in 2018) joakim.nivre@lingfil.uu.se<br />
* Shiqi Zhao (ACL secretary) zhaoshiqi.acl@gmail.com<br />
* Graeme Hirst (ACL treasurer) gh@cs.toronto.edu<br />
* Yejin Choi (ACL board) yejin@cs.washington.edu<br />
* Priscilla Rasmussen (ACL business officer) acl@aclweb.org<br />
* Pascale Fung (AFNLP representative) pascale@ece.ust.hk<br />
* Haizhou Li (AFNLP representative) hli@i2r.a-star.edu.sg<br />
* Yuji Matsumoto (AFNLP representative) matsu@is.naist.jp<br />
* Jong Park (AFNLP representative) park@cs.kaist.ac.kr<br />
<br />
Key Organizers: <br />
<br />
* Claire Cardie, general chair, <cardie@cs.cornell.edu><br />
* Iryna Gurevych, program co-chair, <gurevych@ukp.informatik.tu-darmstadt.de><br />
* Yusuke Miyao, program co-chair, <yusuke@nii.ac.jp> <br />
* Tim Baldwin, local co-chair, <tbaldwin@unimelb.edu.au><br />
* Karin Verspoor, local co-chair, <Karin.Verspoor@unimelb.edu.au><br />
* Trevor Anthony Cohn, local co-chair <t.cohn@unimelb.edu.au><br />
<br />
The committee email list address is: acl18cc@aclweb.org.<br />
<br />
=== Progress ===<br />
<br />
In the last report, we reported on the appointment of Claire Cardie as general chair for the conference, the signing of the contract with Melbourne Convention and Exhibition Centre, and the establishment of the conference website at acl2018.org. <br />
<br />
Since that report:<br />
<br />
* We are very pleased to announce that Iryna Gurevych and Yusuke Miyao has accepted our invitation to the program co-chairs for the conference.<br />
* The general chair has recruited most of the additional conference chairs, including workshop chairs, tutorial chairs, demo chairs, publication chairs, and faculty advisors for the SRW.<br />
* The local co-chairs have appointed a publicity chair, a handbook chair, local sponsorship chairs, and an exhibits coordinator.<br />
<br />
=== Upcoming tasks ===<br />
<br />
We hope to finish these goals in the next couple of weeks to months:<br />
<br />
* Presentation and video of ACL 2018 for presentation at ACL 2017 (responsible: local co-chairs).<br />
* Appointment of remaining chairs: conference handbook chair (responsible: general chair), exhibits coordinator, publicity chair (responsible: local co-chairs).<br />
* Set up an email address for conference chairs (responsible: general chair).<br />
* Make contact with ACL sponsorship committee (responsible: local co-chairs).<br />
* Finalize program chairs' timetable of calls, paper due dates etc. (responsible: program co-chairs).<br />
<br />
After that, key tasks are:<br />
<br />
* Develop conference budget. Estimate registration dates and costs (responsible: general chair, local chairs, and Priscilla).<br />
* Create call for papers, work on finding area chairs and invited speakers (responsible: program chairs).</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2017Q3_Reports:_ACL_2018&diff=717912017Q3 Reports: ACL 20182017-06-27T10:01:30Z<p>JoakimNivre: /* Progress */</p>
<hr />
<div>== ACL 2018 - report by Joakim Nivre ==<br />
<br />
In 2018 there will be an ACL conference in Melbourne, Australia. The conference will take place at the Melbourne Convention and Exhibition Centre, with local organisers from the University of Melbourne. The dates are: July 15-20, 2018.<br />
<br />
=== Coordinating Committee ===<br />
<br />
The conference coordinating committee is:<br />
<br />
* Joakim Nivre (chair; ACL past president in 2018) joakim.nivre@lingfil.uu.se<br />
* Shiqi Zhao (ACL secretary) zhaoshiqi.acl@gmail.com<br />
* Graeme Hirst (ACL treasurer) gh@cs.toronto.edu<br />
* Yejin Choi (ACL board) yejin@cs.washington.edu<br />
* Priscilla Rasmussen (ACL business officer) acl@aclweb.org<br />
* Pascale Fung (AFNLP representative) pascale@ece.ust.hk<br />
* Haizhou Li (AFNLP representative) hli@i2r.a-star.edu.sg<br />
* Yuji Matsumoto (AFNLP representative) matsu@is.naist.jp<br />
* Jong Park (AFNLP representative) park@cs.kaist.ac.kr<br />
<br />
Key Organizers: <br />
<br />
* Claire Cardie, general chair, <cardie@cs.cornell.edu><br />
* Iryna Gurevych, program co-chair, <gurevych@ukp.informatik.tu-darmstadt.de><br />
* Yusuke Miyao, program co-chair, <yusuke@nii.ac.jp> <br />
* Tim Baldwin, local co-chair, <tbaldwin@unimelb.edu.au><br />
* Karin Verspoor, local co-chair, <Karin.Verspoor@unimelb.edu.au><br />
* Trevor Anthony Cohn, local co-chair <t.cohn@unimelb.edu.au><br />
<br />
The committee email list address is: acl18cc@aclweb.org.<br />
<br />
=== Progress ===<br />
<br />
In the last report, we reported on the appointment of Claire Cardie as general chair for the conference, the signing of the contract with Melbourne Convention and Exhibition Centre, and the establishment of the conference website at acl2018.org. <br />
<br />
Since that report:<br />
<br />
* We are very pleased to announce that Iryna Gurevych and Yusuke Miyao has accepted our invitation to the program co-chairs for the conference.<br />
* The general chair has recruited most of the additional conference chairs, including workshop chairs, tutorial chairs, demo chairs, publication chairs, and faculty advisors for the SRW.<br />
* The local co-chairs have appointed a publicity chair, a handbook chair, and an exhibits coordinator.<br />
<br />
=== Upcoming tasks ===<br />
<br />
We hope to finish these goals in the next couple of weeks to months:<br />
<br />
* Presentation and video of ACL 2018 for presentation at ACL 2017 (responsible: local co-chairs).<br />
* Appointment of remaining chairs: conference handbook chair (responsible: general chair), exhibits coordinator, publicity chair (responsible: local co-chairs).<br />
* Set up an email address for conference chairs (responsible: general chair).<br />
* Make contact with ACL sponsorship committee (responsible: local co-chairs).<br />
* Finalize program chairs' timetable of calls, paper due dates etc. (responsible: program co-chairs).<br />
<br />
After that, key tasks are:<br />
<br />
* Develop conference budget. Estimate registration dates and costs (responsible: general chair, local chairs, and Priscilla).<br />
* Create call for papers, work on finding area chairs and invited speakers (responsible: program chairs).</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2017Q3_Reports:_ACL_2018&diff=717902017Q3 Reports: ACL 20182017-06-22T19:39:03Z<p>JoakimNivre: /* Progress */</p>
<hr />
<div>== ACL 2018 - report by Joakim Nivre ==<br />
<br />
In 2018 there will be an ACL conference in Melbourne, Australia. The conference will take place at the Melbourne Convention and Exhibition Centre, with local organisers from the University of Melbourne. The dates are: July 15-20, 2018.<br />
<br />
=== Coordinating Committee ===<br />
<br />
The conference coordinating committee is:<br />
<br />
* Joakim Nivre (chair; ACL past president in 2018) joakim.nivre@lingfil.uu.se<br />
* Shiqi Zhao (ACL secretary) zhaoshiqi.acl@gmail.com<br />
* Graeme Hirst (ACL treasurer) gh@cs.toronto.edu<br />
* Yejin Choi (ACL board) yejin@cs.washington.edu<br />
* Priscilla Rasmussen (ACL business officer) acl@aclweb.org<br />
* Pascale Fung (AFNLP representative) pascale@ece.ust.hk<br />
* Haizhou Li (AFNLP representative) hli@i2r.a-star.edu.sg<br />
* Yuji Matsumoto (AFNLP representative) matsu@is.naist.jp<br />
* Jong Park (AFNLP representative) park@cs.kaist.ac.kr<br />
<br />
Key Organizers: <br />
<br />
* Claire Cardie, general chair, <cardie@cs.cornell.edu><br />
* Iryna Gurevych, program co-chair, <gurevych@ukp.informatik.tu-darmstadt.de><br />
* Yusuke Miyao, program co-chair, <yusuke@nii.ac.jp> <br />
* Tim Baldwin, local co-chair, <tbaldwin@unimelb.edu.au><br />
* Karin Verspoor, local co-chair, <Karin.Verspoor@unimelb.edu.au><br />
* Trevor Anthony Cohn, local co-chair <t.cohn@unimelb.edu.au><br />
<br />
The committee email list address is: acl18cc@aclweb.org.<br />
<br />
=== Progress ===<br />
<br />
In the last report, we reported on the appointment of Claire Cardie as general chair for the conference, the signing of the contract with Melbourne Convention and Exhibition Centre, and the establishment of the conference website at acl2018.org. <br />
<br />
Since that report:<br />
<br />
* We are very pleased to announce that Iryna Gurevych and Yusuke Miyao has accepted our invitation to the program co-chairs for the conference.<br />
* We are also pleased to report that the general chair has recruited most of the additional conference chairs, including workshop chairs, tutorial chairs, demo chairs, publication chairs, and faculty advisors for the SRW.<br />
<br />
=== Upcoming tasks ===<br />
<br />
We hope to finish these goals in the next couple of weeks to months:<br />
<br />
* Presentation and video of ACL 2018 for presentation at ACL 2017 (responsible: local co-chairs).<br />
* Appointment of remaining chairs: conference handbook chair (responsible: general chair), exhibits coordinator, publicity chair (responsible: local co-chairs).<br />
* Set up an email address for conference chairs (responsible: general chair).<br />
* Make contact with ACL sponsorship committee (responsible: local co-chairs).<br />
* Finalize program chairs' timetable of calls, paper due dates etc. (responsible: program co-chairs).<br />
<br />
After that, key tasks are:<br />
<br />
* Develop conference budget. Estimate registration dates and costs (responsible: general chair, local chairs, and Priscilla).<br />
* Create call for papers, work on finding area chairs and invited speakers (responsible: program chairs).</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=2017Q3_Reports:_ACL_2018&diff=717892017Q3 Reports: ACL 20182017-06-22T19:37:51Z<p>JoakimNivre: Created page with "== ACL 2018 - report by Joakim Nivre == In 2018 there will be an ACL conference in Melbourne, Australia. The conference will take place at the Melbourne Convention and Exhibi..."</p>
<hr />
<div>== ACL 2018 - report by Joakim Nivre ==<br />
<br />
In 2018 there will be an ACL conference in Melbourne, Australia. The conference will take place at the Melbourne Convention and Exhibition Centre, with local organisers from the University of Melbourne. The dates are: July 15-20, 2018.<br />
<br />
=== Coordinating Committee ===<br />
<br />
The conference coordinating committee is:<br />
<br />
* Joakim Nivre (chair; ACL past president in 2018) joakim.nivre@lingfil.uu.se<br />
* Shiqi Zhao (ACL secretary) zhaoshiqi.acl@gmail.com<br />
* Graeme Hirst (ACL treasurer) gh@cs.toronto.edu<br />
* Yejin Choi (ACL board) yejin@cs.washington.edu<br />
* Priscilla Rasmussen (ACL business officer) acl@aclweb.org<br />
* Pascale Fung (AFNLP representative) pascale@ece.ust.hk<br />
* Haizhou Li (AFNLP representative) hli@i2r.a-star.edu.sg<br />
* Yuji Matsumoto (AFNLP representative) matsu@is.naist.jp<br />
* Jong Park (AFNLP representative) park@cs.kaist.ac.kr<br />
<br />
Key Organizers: <br />
<br />
* Claire Cardie, general chair, <cardie@cs.cornell.edu><br />
* Iryna Gurevych, program co-chair, <gurevych@ukp.informatik.tu-darmstadt.de><br />
* Yusuke Miyao, program co-chair, <yusuke@nii.ac.jp> <br />
* Tim Baldwin, local co-chair, <tbaldwin@unimelb.edu.au><br />
* Karin Verspoor, local co-chair, <Karin.Verspoor@unimelb.edu.au><br />
* Trevor Anthony Cohn, local co-chair <t.cohn@unimelb.edu.au><br />
<br />
The committee email list address is: acl18cc@aclweb.org.<br />
<br />
=== Progress ===<br />
<br />
In the last report, we reported on the appointment of Claire Cardie as general chair for the conference, the signing of the contract with Melbourne Convention and Exhibition Centre, and the establishment of the conference website at acl2018.org. <br />
<br />
Since that report:<br />
<br />
* We are very pleased to announce that Iryna Gurevych and Yusuke Miyao has accepted our invitation to the program co-chairs for the conference.<br />
* The general chair has recruited most of the additional conference chairs, including workshop chairs, tutorial chairs, demo chairs, publication chairs, and faculty advisors for the SRW.<br />
<br />
=== Upcoming tasks ===<br />
<br />
We hope to finish these goals in the next couple of weeks to months:<br />
<br />
* Presentation and video of ACL 2018 for presentation at ACL 2017 (responsible: local co-chairs).<br />
* Appointment of remaining chairs: conference handbook chair (responsible: general chair), exhibits coordinator, publicity chair (responsible: local co-chairs).<br />
* Set up an email address for conference chairs (responsible: general chair).<br />
* Make contact with ACL sponsorship committee (responsible: local co-chairs).<br />
* Finalize program chairs' timetable of calls, paper due dates etc. (responsible: program co-chairs).<br />
<br />
After that, key tasks are:<br />
<br />
* Develop conference budget. Estimate registration dates and costs (responsible: general chair, local chairs, and Priscilla).<br />
* Create call for papers, work on finding area chairs and invited speakers (responsible: program chairs).</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Fellows_Program&diff=71788Fellows Program2017-06-21T15:24:17Z<p>JoakimNivre: /* Fellows Nominating Committee */</p>
<hr />
<div>== ACL Fellows Program ==<br />
<br />
The ACL Fellows program intends to recognize individuals who have made outstanding contributions to the association or to the field of computational linguistics in general. A person shall be qualified as a candidate for being ACL Fellow if the candidate has made significant contributions in areas including but not limited to the following:<br />
<br />
# Scientific and technical excellence: Important technical contributions to computational linguistics. This should be interpreted in a broad sense to include research and technical development, contributions to academic, government or industrial group efforts, and release of software and resources. Evidence of technical contributions is typically in the form of technical results, publications, patents, and awards but other relevant forms of evidence should be considered as well. <br />
# Service excellence: Extended service to the ACL or other scientific organizations whose mission aligns with that of the ACL. This includes being a member of a board or executive committee, being the editor of a journal, serving in major conference chair positions, or doing other voluntary work of significance for the organization. <br />
# Enabling excellence: Significant educational and outreach activities with broader impact. This includes contributions to improve the visibility and impact of computational linguistics in society as a whole, such as the development and promotion of educational programs, raising awareness of equity and diversity issues, building bridges between academia and industry, or collaborating with government agencies and other pro-societal organizations.<br />
<br />
Qualified candidates are furthermore expected to observe accepted professional and ethical standards both within and outside their scientific activities. <br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
=== Procedure for Selecting New Fellows ===<br />
<br />
# Nominations for new Fellows can be made by any current ACL member and need to be supported by recommendations from two additional ACL members.<br />
# To be eligible, the nominee must have been a member of the ACL for 3 out of the last 5 calendar years, including the year when they are nominated.<br />
# Nominations and supporting recommendations must be submitted using the special form available at <link coming soon>.<br />
# The deadline for nominations each year is October 1.<br />
# The selection of new fellows from the pool of nominees is handled by the ACL Nominating Committee, consisting of three past ACL presidents and six ACL Fellows. <br />
# The committee is charged with soliciting a large and diverse pool of candidates and with making the final selection in accordance with the criteria stated above.<br />
# The selection of the committee will be submitted for formal approval to the ACL executive, providing whatever explanations and supporting documentation the Executive requires.<br />
# The role of the Executive is to ensure consistency and clarity in the decision process, and they should not overrule the committee’s proposal or advance alternative candidates. <br />
# The number of new fellows appointed in a year should not represent more than 0.2% of the current ACL membership.<br />
<br />
=== Fellows Nominating Committee === <br />
<br />
The membership recently amended the [[ACL_Constitution]] to designate the makeup of the Nominating Committee for the ACL Fellows as follows: <br />
<br />
:There shall be a Nominating Committee consisting of the three most recent Past Presidents, each serving for the three years following their own Presidency, and six ACL Fellows selected subject to diversity requirements set forth by the Executive. <br />
<br />
The current members of the nominating committee (as of June 21, 2017) are:<br />
<br />
*Pushpak Bhattacharyya<br />
*Nicoletta Calzolari<br />
*Eugene Charniak<br />
*Michael Collins<br />
*Eva Hajicova<br />
*Julia Hirschberg<br />
*Christopher Manning<br />
*Yuji Matsumoto<br />
*Gertjan van Noord (chair)</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Fellows_Program&diff=71747Fellows Program2017-04-03T07:06:40Z<p>JoakimNivre: </p>
<hr />
<div>== ACL Fellows Program ==<br />
<br />
The ACL Fellows program intends to recognize individuals who have made outstanding contributions to the association or to the field of computational linguistics in general. A person shall be qualified as a candidate for being ACL Fellow if the candidate has made significant contributions in areas including but not limited to the following:<br />
<br />
# Scientific and technical excellence: Important technical contributions to computational linguistics. This should be interpreted in a broad sense to include research and technical development, contributions to academic, government or industrial group efforts, and release of software and resources. Evidence of technical contributions is typically in the form of technical results, publications, patents, and awards but other relevant forms of evidence should be considered as well. <br />
# Service excellence: Extended service to the ACL or other scientific organizations whose mission aligns with that of the ACL. This includes being a member of a board or executive committee, being the editor of a journal, serving in major conference chair positions, or doing other voluntary work of significance for the organization. <br />
# Enabling excellence: Significant educational and outreach activities with broader impact. This includes contributions to improve the visibility and impact of computational linguistics in society as a whole, such as the development and promotion of educational programs, raising awareness of equity and diversity issues, building bridges between academia and industry, or collaborating with government agencies and other pro-societal organizations.<br />
<br />
Qualified candidates are furthermore expected to observe accepted professional and ethical standards both within and outside their scientific activities. <br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
=== Procedure for Selecting New Fellows ===<br />
<br />
# Nominations for new Fellows can be made by any current ACL member and need to be supported by recommendations from two additional ACL members.<br />
# To be eligible, the nominee must have been a member of the ACL for 3 out of the last 5 calendar years, including the year when they are nominated.<br />
# Nominations and supporting recommendations must be submitted using the special form available at <link coming soon>.<br />
# The deadline for nominations each year is October 1.<br />
# The selection of new fellows from the pool of nominees is handled by the ACL Nominating Committee, consisting of three past ACL presidents and six ACL Fellows. <br />
# The committee is charged with soliciting a large and diverse pool of candidates and with making the final selection in accordance with the criteria stated above.<br />
# The selection of the committee will be submitted for formal approval to the ACL executive, providing whatever explanations and supporting documentation the Executive requires.<br />
# The role of the Executive is to ensure consistency and clarity in the decision process, and they should not overrule the committee’s proposal or advance alternative candidates. <br />
# The number of new fellows appointed in a year should not represent more than 0.2% of the current ACL membership.</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Selecting_a_Program_Co-Chair&diff=71742Selecting a Program Co-Chair2017-03-31T15:30:05Z<p>JoakimNivre: </p>
<hr />
<div>The Program Committee of the main ACL conference is chaired by two Program Co-Chairs. The Co-Chairs should have:<br />
<br />
* experience as Area Chair for a '''major''' conference in Computational Linguistics or a related area,<br />
* standing as an internationally recognized researcher in Computational Linguistics or a related area,<br />
* good organizational, collaborative and communicative skills.<br />
<br />
When appointing Program Co-Chairs, the coordinating committee should in addition consider the following:<br />
<br />
* ACL wants to promote equality and diversity in the selection of conference chairs.<br />
* The two Program Co-Chairs should have complementary profiles, scientifically as well as socio-geographically<br />
* Candidates who have already been Program Co-Chair of ACL should normally not be considered for the same conference.<br />
* Candidates with experience only from conferences in related areas, not Computational Linguistics, should normally not be considered.<br />
<br />
NB: As '''major''' CL conferences are counted ACL, NAACL, EACL, IJCNLP, COLING, LREC and EMNLP.<br />
Conferences in related areas include, for example, IJCAI, AAAI, NIPS, ICML, CHI, and CSCW.<br />
<br />
For information about roles and responsibilities, see [[Program chair duties|Program Chair duties]].<br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
Author: Joakim Nivre, 2016</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Selecting_a_General_Chair&diff=71741Selecting a General Chair2017-03-31T15:29:35Z<p>JoakimNivre: </p>
<hr />
<div>The General Chair of the main ACL conference should have:<br />
<br />
* experience from at least one (preferably two) of the following conference chair roles:<br />
** Program Chair of a '''major''' international conference in Computational Linguistics or a related area<br />
** Local Arrangements Chair of an international conference in Computational Linguistics or a related area<br />
** General Chair of an international conference in Computational Linguistics or a related area<br />
* a proven capacity for leadership, including good organizational, collaborative and communicative skills.<br />
<br />
When appointing a General Chair, the coordinating committee should in addition consider the following:<br />
<br />
* ACL wants to promote equality and diversity in the selection of conference chairs.<br />
* The General Chair should normally have an affiliation in the geographical region where the conference takes place.<br />
* Candidates who have already been General Chair of the main ACL conference should normally not be considered again.<br />
* Candidates with experience only from conferences in related areas, not Computational Linguistics, should normally not be considered.<br />
<br />
NB: As '''major''' CL conferences are counted ACL, NAACL, EACL, IJCNLP, COLING, LREC and EMNLP.<br />
Conferences in related areas include, for example, IJCAI, AAAI, NIPS, ICML, CHI, and CSCW.<br />
<br />
For information about roles and responsibilities, see [[General (conference) chair duties|General Chair duties]].<br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
Author: Joakim Nivre, 2016</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Fellows_Program&diff=71740Fellows Program2017-03-31T15:27:42Z<p>JoakimNivre: </p>
<hr />
<div>== ACL Fellows Program ==<br />
<br />
The ACL Fellows program intends to recognize individuals who have made outstanding contributions to the association or to the field of computational linguistics in general. A person shall be qualified as a candidate for being ACL Fellow if the candidate has made significant contributions in areas including but not limited to the following:<br />
<br />
# Scientific and technical excellence: Important technical contributions to computational linguistics. This should be interpreted in a broad sense to include research and technical development, contributions to academic, government or industrial group efforts, and release of software and resources. Evidence of technical contributions is typically in the form of technical results, publications, patents, and awards but other relevant forms of evidence should be considered as well. <br />
# Service excellence: Extended service to the ACL or other scientific organizations whose mission aligns with that of the ACL. This includes being a member of a board or executive committee, being the editor of a journal, serving in major conference chair positions, or doing other voluntary work of significance for the organization. <br />
# Enabling excellence: Significant educational and outreach activities with broader impact. This includes contributions to improve the visibility and impact of computational linguistics in society as a whole, such as the development and promotion of educational programs, raising awareness of equity and diversity issues, building bridges between academia and industry, or collaborating with government agencies and other pro-societal organizations.<br />
<br />
Qualified candidates are furthermore expected to observe accepted professional and ethical standards both within and outside their scientific activities. <br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
=== Procedure for Selecting New Fellows ===<br />
<br />
# Nominations for new Fellows can be made by any current ACL member and need to be supported by recommendations from two additional ACL members.<br />
# To be eligible, the nominee must have been a member of the ACL for 3 out of the last 5 calendar years, including the year when they are nominated.<br />
# Nominations and supporting recommendations must be submitted using the special form available ???<br />
# The deadline for nominations each year is October 1.<br />
# The selection of new fellows from the pool of nominees is handled by the ACL Nominating Committee, consisting of three past ACL presidents and six ACL Fellows. <br />
# The committee is charged with soliciting a large and diverse pool of candidates and with making the final selection in accordance with the criteria stated above.<br />
# The selection of the committee will be submitted for formal approval to the ACL executive, providing whatever explanations and supporting documentation the Executive requires.<br />
# The role of the Executive is to ensure consistency and clarity in the decision process, and they should not overrule the committee’s proposal or advance alternative candidates. <br />
# The number of new fellows appointed in a year should not represent more than 0.2% of the current ACL membership.</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Promoting_Diversity_and_Avoiding_Bias&diff=71739Promoting Diversity and Avoiding Bias2017-03-31T15:26:33Z<p>JoakimNivre: </p>
<hr />
<div>== Promoting Diversity and Avoiding Bias ==<br />
<br />
The ACL is committed to promoting equity and diversity at all levels of the organization. We believe an important step towards a more inclusive community is to raise awareness of the ways in which stereotypes and unconscious biases can undermine the goal of equal opportunities for all our members and point to ways in which this can be avoided. We think the resources listed below can help us achieve this goal, and we encourage all our members to use them, especially those who are involved in nomination and selection committees. We welcome suggestions for further resources that can be added.<br />
<br />
*Two videos on unconscious bias:<br />
**[https://www.youtube.com/watch?v=nLjFTHTgEVU Google HR on “Avoiding Unconscious Bias”]<br />
**[https://www.youtube.com/watch?v=YPoymWLNjVk Stanford Prof. Shelley Correll on “Creating a Level Playing Field”]<br />
*[http://blogs.lse.ac.uk/impactofsocialsciences/2016/03/08/gender-bias-in-academe-an-annotated-bibliography/ Gender Bias in Academe: An annotated Bibliography of Important Recent Studies]<br />
*[https://implicit.harvard.edu/implicit/takeatest.html Implicit Association Tests (IAT) to check your own implicit biases]<br />
**For example (3 out of 13): Gender-Science IAT, Skin-Tone IAT, Sexuality IAT<br />
*[https://scs4all.cs.cmu.edu/biasbusters/ Bias Busters @ CMU] for more pointers and resources</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Promoting_Diversity_and_Avoiding_Bias&diff=71738Promoting Diversity and Avoiding Bias2017-03-31T15:25:50Z<p>JoakimNivre: Created page with "== Promoting Diversity and Avoiding Bias == The ACL is committed to promoting equity and diversity at all levels of the organization. We believe an important step towards a m..."</p>
<hr />
<div>== Promoting Diversity and Avoiding Bias ==<br />
<br />
The ACL is committed to promoting equity and diversity at all levels of the organization. We believe an important step towards a more inclusive community is to raise awareness of the ways in which stereotypes and unconscious biases can undermine the goal of equal opportunities for all our members and point to ways in which this can be avoided. We think the resources listed below can help us achieve this goal, and we encourage all our members to use them, especially those who are involved in nomination and selection committees. We welcome suggestions for further resources that can be added.<br />
<br />
*Two videos on unconscious bias:<br />
**[https://www.youtube.com/watch?v=nLjFTHTgEVU Google HR on “Avoiding Unconscious Bias”]<br />
**[https://www.youtube.com/watch?v=YPoymWLNjVk Stanford Prof. Shelley Correll on “Creating a Level Playing Field”]<br />
*[http://blogs.lse.ac.uk/impactofsocialsciences/2016/03/08/gender-bias-in-academe-an-annotated-bibliography/ Gender Bias in Academe: An annotated Bibliography of Important Recent Studies]<br />
*[https://implicit.harvard.edu/implicit/takeatest.html Implicit Association Tests (IAT) to check your own implicit biases]<br />
**For example (3 out of 13): Gender-Science IAT, Skin-Tone IAT, Sexuality IAT<br />
*[https://scs4all.cs.cmu.edu/biasbusters/ Bias Busters @ CMU for more pointers and resources]</div>JoakimNivrehttps://www.aclweb.org/adminwiki/index.php?title=Lifetime_Achievement_Award&diff=71737Lifetime Achievement Award2017-03-31T15:19:50Z<p>JoakimNivre: </p>
<hr />
<div>== Procedure for Determining ACL LTA Recipient ==<br />
<br />
The purpose of the these Principles and Procedure is to ensure a) due<br />
diligence; b) continuity; and c) confidentiality.<br />
<br />
=== Principles ===<br />
<br />
The ACL Lifetime Achievement award is, as its name indicates, a<br />
recognition for widely recognized, sustained, and enduring<br />
contributions to our field over a long period. It is not awarded<br />
merely for outstanding recent contributions to a currently hot topic.<br />
<br />
Candidates for the award will generally be senior, with a working<br />
lifetime of contributions, even though they will often be active in<br />
research. There may be issues of timeliness.<br />
<br />
These considerations make the decison to make an award highly<br />
sensitive. It is important that the award be seen by the membership<br />
as appropriate and timely. There may be issues of representation.<br />
Above all, there should not be any widespread perception that a<br />
deserving candidate has been passed over.<br />
<br />
It follows that there is a responsibility on the executive to not<br />
merely seek advocacy, but also maintain a consistent and<br />
continuous collective wisdom concerning people in the field who<br />
should be considered by the current Executive and future ones. It<br />
should not be possible for someone to be passed over by accident.<br />
<br />
We do not have to make an award every year.<br />
<br />
'''NB:''' ACL is committed to promoting equity and diversity at all levels of <br />
the organization. Everyone involved in nomination and selection procedures <br />
is therefore encouraged to consult our page with resources for <br />
[[Promoting Diversity and Avoiding Bias]].<br />
<br />
=== Procedure ===<br />
<br />
# The selection of the recipient of the LTA Award is handled by the ACL Nominating Committee, consisting of three past ACL presidents and six ACL Fellows. The committee is charged with coming up with a single candidate under the above principles.<br />
# The committee may call for nominations from the ACL Executive, to be considered together with their own nominations as well as updates of any nominations carried forward from previous years. New recommendations and updates should take the form of a written case addressing eligibility under the criteria for the award.<br />
# The committee will strive to converge on unanimous support for a candidate for the current year. The committee will seek advice from respected impartial senior figures in the field, such as previous recipients of the award.<br />
# The committee will propose the candidate for the approval of the ACL executive, providing whatever explanations and supporting documentation the Executive requires, and commenting on other cases that should be carried forward for future consideration. The role of the Executive is to ensure consistency and clarity in the decision process, and they should not overrule the committee’s proposal or advance alternative candidates. <br />
# The ACL secretary will be responsible for confidential safe-keeping of dossiers if the committee wishes to pass on candidates to next year’s committee. <br />
<br />
Further steps:<br />
<br />
# The ACL President will call the awardee to convey the news [travel support etc?]<br />
# Once the awardee has been informed, the Journal editor will contact the awardee to make arrangements for publishing his/her talk in the Journal. Publication processing times mean that the awardee needs to provide the editor with the manuscript for publication typically within a few weeks of the conference at which the talk is presented, so the awardee needs to be informed of this several months before the conference to allow sufficient time for preparation.</div>JoakimNivre