[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[eu_members at aclweb dot org] Sweden: Fourteenth Conference on Computational Natural Language Learning (CoNLL-2010) -- CFP



======================================================================
CoNLL-2010
Fourteenth Conference on Computational Natural Language Learning
Uppsala, Sweden
July 15-16, 2010
http://www.cnts.ua.ac.be/conll/

======================================================================
Call for Papers
======================================================================

CoNLL is the yearly international conference on natural language
learning organized by SIGNLL (the ACL Special Interest Group on
Natural Language Learning). This year, CoNLL will be collocated with
ACL 2010 in Uppsala, Sweden.

Important Dates
---------------

 * Paper submission deadline: March 8, 2010, 23:59 GMT

 * Notification of acceptance: April 15

 * Camera-ready copy deadline: May 6

 * Conference: July 15-16


Topics
------

We invite submission of papers about natural language learning
topics including:

 * Supervised, unsupervised and semi-supervised machine learning
   methods applied to natural language

 * Computational models of human language acquisition and processing

 * Optimisation methods and inference algorithms for natural language

 * Active learning for natural language processing tasks

 * Computational learning theory analysis of language learning

 * Empirical and theoretical comparisons of language learning methods
   including novel evaluation methods

 * Computational models of language evolution and historical change

 * Algorithms for grammatical inference applied to natural language

See http://ifarm.nl/signll/ and http://ifarm.nl/signll/conll/ for more
information about SIGNLL and CoNLL.


Invited Speakers
----------------

 * Lillian Lee (Cornell University)
 * Zoubin Ghahramani (University of Cambridge)


Special Topic of Interest
-------------------------

This year in CoNLL-2010 the special topic of interest is:

       Grammar induction

We encourage submissions on papers relating to grammar induction, from
a machine learning, natural language engineering and cognitive
perspective. We wish to bring together researchers working on varying
aspects of grammar learning in a number of different areas including
statistical methods, pattern recognition, neural networks,
computational linguistics, computational learning theory, automata
theory, and language acquisition.  Specifically, we encourage
submissions of papers addressing:

 * Different models of grammar induction: e.g., learning from
   examples, learning using examples and queries, incremental versus
   non-incremental learning, distribution-free models of learning,
   learning under various distributional assumptions, learning from
   single versus multiple languages, learning synchronous grammars.

 * Different settings for grammar induction: unsupervised and
   semi-supervised approaches to grammar induction; supervised learning
   augmented by grammar induction techniques, e.g. state splitting
   using latent grammar symbols. Online learning, bootstrapping
   approaches, and Bayesian approaches to grammar induction

 * Theoretical results in grammar induction of formal languages
   with application to natural language learning: e.g., impossibility
   results, complexity results, characterizations of representational
   and search biases of grammar induction algorithms.

 * Cognitive models of grammar induction: e.g., models that faithfully
   represent the cognitive operations involved in human language
   acquisition or models that help explain facts about grammar
   acquisition (e.g., poverty of the stimulus).

 * Empirical comparison of different approaches to grammar induction.

 * Demonstrated or potential applications of grammar induction in
   natural language processing, machine translation, dialogue systems,
   computational biology, structural pattern recognition, adaptive
   intelligent agents, and other domains.


Best Paper Award
----------------

As in previous CoNLL conferences, a Best Paper Award will be given to
the authors of the highest quality paper. The most important aspects
in judging the quality of a paper for this award will be: originality,
innovativeness, relevance, and impact of the presented research.


Main Session Submission Details
-------------------------------

A paper submitted to CoNLL-2010 must describe original, unpublished
work. Submit a full paper by March 8 2009, 23:59 GMT. Papers must
have at most 8 pages of content, plus any number of pages that
contain references. Submission must be done electronically through
the web form at:

https://www.softconf.com/acl2010/acl2010conll/submit.html

We require the use of the ACL 2010 LaTeX style files or Microsoft
Word Style files tailored for this year's conference.  Papers must
conform to the official ACL 2010 style guidelines.  Authors who are
unable to use these style files or submit a PDF file electronically
should contact the program co-chairs.

Since reviewing will be blind, the paper should not include the
authors' names and affiliations, and there should be no
self-references that reveal the authors' identity. In the submission
form, you will be asked for the following information: paper title,
authors' names, affiliations, and email addresses, contact author's
email address, a list of keywords, abstract, and an indication of
whether the paper has been simultaneously submitted to other
conferences (and if so which conferences). The contact author of an
accepted paper under multiple submissions should inform the program
co-chairs immediately whether he or she intends the accepted paper to
appear in CoNLL-2010.  A paper that appears in CoNLL-2010 must be
withdrawn from other conferences.

Authors of accepted submissions are to produce a final paper to be
published in the proceedings of the conference, which will be
available at the conference for participants, and distributed
afterwards by ACL. Final papers must also follow the ACL 2010 style
and should have at most 8 pages of content plus extra pages for
references only.  The camera ready submission deadline is listed
above.  At least one author is expected to register for the conference
and present the paper. Please do not submit a paper if you do not
plan to attend the conference.

As in previous years, CoNLL-2010 will include a shared task which is
organized by a separate committee. The details of the shared task are
included in this CFP (see below). Please note the different submission
details and deadlines for the shared task.


Conference Chairs
-----------------

Anoop Sarkar
School of Computing Science
Simon Fraser University
anoop (at) cs.sfu.ca

Mirella Lapata
School of Informatics
University of Edinburgh
mlap (at) inf.ed.ac.uk

For the full program committee please visit the CoNLL-2010 website:
http://www.cnts.ua.ac.be/conll/


Shared Task
-----------

"Learning to detect hedges and their scope in natural language texts"

In Natural Language Processing (NLP) - in particular, in Information
Extraction (IE) - many applications aim at extracting factual
information from text. In order to distinguish facts from unreliable
or uncertain information, linguistic devices such as hedges
(indicating that authors do not or cannot back up their
opinions/statements with facts) have to be identified. Applications
should handle detected speculative parts in a different manner.  Hedge
detection has received considerable interest recently in the
biomedical NLP community, including research papers addressing the
detection of hedge devices in biomedical texts, and some recent work
on detecting the in-sentence scope of hedge cues in text.  Exploiting
the hedge scope annotated BioScope corpus and publicly available
Wikipedia texts, the goals of the Shared Task are 1) learning to
detect hedge cues in natural language texts and 2) learning to resolve
the in-sentence scope of hedge cues.

The task is described in detail in its own Call for Participation at
http://www.inf.u-szeged.hu/rgai/conll2010st

Shared Task contact email: rfarkas (at) inf.u-szeged.hu
(Richard Farkas, University of Szeged)

Shared Task tentative dates and deadlines:

 * January 11, 2010: release of trial datasets and scorer;

 * January 18, 2010: registration for the task opens;

 * February 1, 2010: training and development sets available;

 * March 28, 2010: test set available;

 * April 2, 2010: systems' outputs collected;

 * April 18, 2010: deadline for system paper submission;

 * May 2, 2010: notification of acceptance;

 * May 9: deadline for camera ready paper submission.


Shared Task Submissions
-----------------------

See the shared task web page for detailed instructions at
http://www.inf.u-szeged.hu/rgai/conll2010st


Shared Task Organizers
----------------------

Richard Farkas, Human Language Technology Group, University of Szeged
(rfarkas at inf.u-szeged.hu)

Organizers:

 * Veronika Vincze, Human Language Technology Group, University of
   Szeged (vinczev at inf.u-szeged.hu)

 * Gyorgy Szarvas, Ubiquitous Knowledge Processing (UKP) Lab,
   Technische Universitaat Darmstadt
   (szarvas at tk.informatik.tu-darmstadt.de)

 * Gyorgy Mora, Human Language Technology Group, University of Szeged
   (gymora at inf.u-szeged.hu)

 * Janos Csirik, Research Group of Artificial Intelligence, Hungarian
   Academy of Sciences (csirik at inf.u-szeged.hu)


Information Officer
-------------------

Erik Tjong Kim Sang
University of Groningen (The Netherlands)
erikt (at) xs4all.nl