== WORKSHOP DESCRIPTION ==
The Second Workshop on “New Frontiers in Summarization workshop” at EMNLP 2019 aims to provide a research forum for cross-fertilization of ideas. We seek to bring together researchers from a diverse range of fields (e.g., summarization, visualization, language generation, cognitive and psycholinguistics) for discussion on key issues related to automatic summarization. This includes discussion on novel paradigms/frameworks, shared tasks of interest, information integration and presentation, applied research and applications, and possible future research foci. The workshop will pave the way towards building a cohesive research community, accelerating knowledge diffusion, developing new tools, datasets and resources that are in line with the needs of academia, industry, and government.
While much has been accomplished, there is more yet to do. New advances in natural language processing (e.g., deep neural networks) have resulted in state-of-the-art performance according to existing standards of summarization evaluation, by effectively exploiting large-scale datasets and superior computing power. This progress now needs to be complemented in at least two ways. On the one hand, the summarization of large amount of multimodal data (text + others) needs more sophisticated abstraction capabilities, better integration of abstraction and extraction, more flexible language generation, as well as the ability to combine language with information visualization. On the other hand, to assess the quality of such system summaries, more comprehensive evaluation metrics are needed which correlate more tightly with human judges or extrinsic task-based performance. Both of these pillars will be crucial for realistic, ecologically valid deployment of summarization research.
== TOPICS ==
- Abstractive and extractive summarization
- Language generation
- Multiple text genres (News, tweets, product reviews, meeting conversations, forums, lectures, student feedback, emails, medical records, books, research articles, etc)
- Multimodal Input: Information integration and aggregation across multiple modalities (text, speech, image, video)
- Multimodal Output: Summarization and visualization + interactive exploration
- Tailoring summaries to user queries or interests
- Semantic aspects of summarization (e.g. semantic representation, inference, validity)
- Development of new algorithms (e.g. integrating neural and non-neural, distant supervision)
- Development of new datasets and annotations
- Development of new evaluation metrics
- Cognitive or psycholinguistic aspects of summarization and visualization (e.g. perceived readability, usability, etc)
== SUBMISSIONS ==
Both long paper (eight (8) pages with unlimited reference) and short paper (four (4) pages with two-page unlimited reference) are welcomed for submission!
For the workshop this year, we are experimenting with a new reviewing model, where reviews and review quality ratings (link to the questionnaire for reviewers, link to the questionnaire for authors) will be collected for a research project (by Northeastern University and OpenReview) on peer review quality analysis.
To achieve this goal, two review systems will be used: START and OpenReview. Here is a quick breakdown of the process:
-- Authors upload the initial submission to BOTH systems (START and OpenReview) by paper submission deadline.
-- Reviewers and PCs post reviews and acceptance decisions on OpenReview, to allow data collection via a customized web interface. We follow the standard DOUBLE-BLIND policy, and the submissions and reviews will NEVER be visible to the public, except to authors, reviewers, and PCs.
-- Authors upload the camera-ready version to START, to facilitate the production of EMNLP workshop proceedings.
All collected data (anonymous reviews and review quality ratings, not including submissions) will be used for research purpose only, and we MAY release the dataset to the broader research community in the future (at least 6 months after the decisions are made). Authors are encouraged, but not required, to provide review quality ratings. Authors have the right to exclude data associated with their submission from the released dataset (can be indicated upon submission).
Submission URLs:
START (for initial submission and camera-ready): https://www.softconf.com/emnlp2019/ws-NEWSUM/
OpenReview (for initial submission only): https://openreview.net/group?id=EMNLP/2019/Workshop/Summarization
More information can be found at https://summarization2019.github.io/submission/
== INVITED SPEAKERS ==
Wenjie Li (The Hong Kong Polytechnic University, Hong Kong)
Manabu Okumura (Tokyo Institute of Technology)
More to announce!
== IMPORTANT DATES ==
Submissions Deadline: August 19, 2019 everywhere in the world
Acceptance Notification: September 16, 2019
Camera-Ready Due: September 30, 2019
Workshop Date: November 4, 2019
== ORGANIZERS ==
Lu Wang (Northeastern University)
Giuseppe Carenini (University of British Columbia)
Jackie Chi Kit Cheung (McGill University)
Fei Liu (University of Central Florida)
== PROGRAM COMMITTEE
Asli Celikyilmaz (Microsoft Research)
Hou Pong Chan (The Chinese University of Hong Kong)
Jianpeng Cheng (University of Edinburgh)
Yuntian Deng (Harvard University)
Yue Dong (McGill University)
Greg Durrett (The University of Texas at Austin)
Michael Elhadad (Ben‑Gurion University of the Negev)
Benoit Favre (Aix-Marseille University)
Wei Gao (Victoria University of Wellington)
Sebastian Gehrmann (Harvard University)
Enamul Hoque (York University)
Chen Li (Tencent AI lab)
Sujian Li (Peking University)
Wenjie Li (The Hong Kong Polytechnic University,)
Mijail Kabadjov (University of Essex)
Kundan Krishna (CMU)
Yashar Mehdad (Facebook)
Gabriel Murray (University of the Fraser Valley)
Courtney Napoles (Johns Hopkins University)
Shashi Narayan (Edinburgh University)
Jun-Ping Ng (Amazon)
Manabu Okumura (Tokyo Institute of Technology Institute of Innovative Research)
Romain Paulus (Salesforce)
Ramakanth Pasunuru (UNC Chapel Hill)
Maxime Peyrard (TU Darmstadt)
Horacio Saggion (Universitat Pompeu Fabra)
Abigail See (Stanford)
Hiroya Takamura (Tokyo Institute of Technology)
Simone Teufel (University of Cambridge)
Xiaojun Wan (Peking University)
Sam Wiseman (TTIC)
Rui Yan (Peking University)
== WEBSITE ==
http://summarization2019.github.io/