Event Notification Type: 
Call for Papers
Jeju Island
Thursday, 12 July 2012 to Saturday, 14 July 2012
Contact Email: 
James Henderson
Submission Deadline: 
Wednesday, 28 March 2012

First Call for Papers for EMNLP-CoNLL 2012

Joint meeting of
Conference on Empirical Methods in Natural Language Processing
Conference on Computational Natural Language Learning
Jeju Island, Korea
July 12-14, immediately after ACL 2012

SIGDAT (the ACL Special Interest Group on Linguistic Data and Corpus-based
Approaches to NLP) and SIGNLL (the ACL Special Interest Group on Natural
Language Learning) invite submissions to EMNLP-CoNLL 2012. The conference
will be held July 12-14, 2012, at the International Convention Center on Jeju
Island, Korea, immediately following ACL 2012.

Important Dates

* March 28, 2012: Paper submission deadline
* May 1-4, 2012: Author response period
* May 18, 2012: Acceptance notification
* June 3, 2012: Camera ready papers due
* July 12-14, 2012: EMNLP-CoNLL conference

All deadlines refer to 23:59 PST (UTC/GMT-8 hours; Los Angeles time zone)


We solicit papers on all areas that may be of interest to the SIGDAT and
SIGNLL communities, including but not limited to:

* Phonology and morphology, tagging and chunking, segmentation
* Syntax and parsing
* Semantics
* Discourse, dialog, and pragmatics
* Summarization and generation
* Machine translation
* Information retrieval and question answering
* Information extraction
* Spoken language processing
* Text mining and natural language processing applications
* Multilinguality
* Sentiment analysis and opinion mining
* Models of language in social context
* NLP for the Web
* Computational models of human language acquisition
* Supervised, unsupervised and semi-supervised machine learning
methods applied to natural language, including speech
* Statistical methods (Bayesian learning, graphical models, kernel
methods, statistical models for structured problems)
* Symbolic learning methods (rule induction and decision tree
learning, lazy learning, inductive logic programming, analytical
learning, transformation-based error-driven learning)
* Biologically-inspired methods (Neural Networks, Evolutionary Computing)
* Reinforcement learning, active learning
* Learning architectures for structural and relational NLP tasks
* Computational models of language evolution and historical change
* Computational learning theory analysis of language learning
* Empirical and theoretical comparisons of language learning
methods, including novel evaluation methods
* Models of induction and analogy in linguistics


Submissions should describe original, unpublished work. Papers presented
at EMNLP-CoNLL should mainly contain new material that has not been presented
at any other meeting with publicly available proceedings. Papers that
have been or will be submitted to other meetings or publications must
disclose this information at submission time. Please list all other
meetings where the paper has been submitted in the "other submissions"
field on the submission site.

Each submission consists of a paper of up to nine (9) pages of content
and any number of additional pages containing references only, together
with optional supplementary material as described below. The paper
must conform to the official ACL 2012 style guidelines. Please use
the official ACL 2012 style files
for the paper. We reserve the right to reject submissions if the paper
does not conform to these styles, including letter size and font size

Since reviewing will be blind, the submission should not include the
authors' names and affiliations. Furthermore, self-references that
reveal the author's identity, e.g., "We previously showed (Smith, 1991)
...", should be avoided. Instead, use citations such as "Smith (1991)
previously showed ...". Submissions that do not conform to these
requirements will be rejected without review. Separate author
identification information is required as part of the on-line submission

The *supplementary material* should be supplementary (rather than
central) to the paper. It may include explanations or details of proofs
or derivations that do not fit into the paper, lists of features or
feature templates, sample inputs and outputs for a system, pseudo-code
or source code, and data. Any information that is critical to
understanding the paper should be included within the paper itself.
While the paper may refer to and cite the supplementary material and the
supplementary material will be available to reviewers, they will not be
asked to review or even download the supplementary material.

Submission and reviewing will be on-line, managed by the START system.
The only accepted format for submitted papers is PDF. The
supplementary material must be in the form of a single .zip or a .tgz
archive file with a maximum size of 10MB; otherwise there are no
constraints on its format. Submissions, together with all supplementary
material, must be uploaded onto the START system by the submission
deadlines; submissions submitted after that time will not be reviewed.
To minimize network congestion we request authors upload their
submissions as early as possible (especially if they contain large
supplementary material files).

Authors of accepted submissions are to produce a final paper to be
published in the proceedings of the conference. Final papers must follow
the same style and length requirements as submitted papers. If an
accepted submission has also been submitted elsewhere, the contact
author must promptly inform the program co-chairs whether he or she
intends the accepted paper to be included in EMNLP-CoNLL, and if so must
withdraw the paper from other meetings or publications. At least one
author must register for the conference and present the paper. Papers
will be presented orally or as a poster presentation, as determined by
the program committee. The decisions as to which papers will be
presented orally and which as poster presentations will be based on the
nature rather than on the quality of the work, and there will be no
distinction between them in the proceedings.


General Chair:

* Jun'ichi Tsujii, Microsoft Research Asia

Program Co-Chairs:

* James Henderson, University of Geneva
* Marius Pasca, Google

Publication Chair:

* Naoaki Okazaki, University of Tohoku

Contact email: emnlp-conll2012@unige.ch

Shared Task:
Modeling Multilingual Unrestricted Coreference in OntoNotes

EMNLP-CoNLL 2012 will continue the CoNLL tradition of having the highest
profile shared task in the NLP world. This year's task will be
automatic anaphoric mention detection and coreference resolution using
the English, Chinese and Arabic language portions of the OntoNotes 5.0
data given predicted information on the other layers.

The shared task is described in its own Call for Participation at
http://aclweb.org/portal/content/conll-2012-shared-task. For detailed
information and submissions, please see the shared task web page at
http://conll.cemantix.org/2012. Questions about the CoNLL-2012 shared
task can be sent to conll-2012-st@cemantix.org.

In order to receive future calls and other information about the shared
task, participants should register their intent to participate, in
either or both of the two tracks, by sending an e-mail to
conll-2012-st@cemantix.org. Although the deadline for registration is
not until January 22, 2012, we recommend participants to register as
early as possible, in order not to miss any information.

Shared Task Important Dates

* December 28, 2011: Registration begins
* January 22, 2012: Trial data available
* February 10, 2012: Registration deadline
* February 19, 2012: Training and development set available
* April 22, 2012: Test set available
* April 26, 2012: System outputs collected
* April 29, 2012: System results due to participants
* May 6, 2012: System papers due
* May 15, 2012: Reviews back to authors
* May 22, 2012: Camera ready papers due
* July 12-14, 2012: EMNLP-CoNLL conference

Shared Task Organizers

* Sameer Pradhan (Chair), Raytheon BBN Technologies
* Alessandro Moschitti, University of Trento
* Nianwen Xue, Brandeis University

Advisory Committee: Mitchell Marcus, University of Pennsylvania;
Martha Palmer, University of Colorado; Lance Ramshaw, Raytheon BBN
Technologies; Ralph Weischedel, Raytheon BBN Technologies.


See http://www.sigdat.org/ for more information about SIGDAT, and see
http://ifarm.nl/signll/ for more information about SIGNLL.