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

[eu_members at aclweb dot org] CoNLL 2009 Shared Task -- Call for Participation

                  CALL FOR PARTICIPATION
                  CoNLL 2009 Shared Task

 Syntactic and Semantic Dependencies in Multiple Languages

The task for CoNLL 2009 is an extension of the CoNLL 2008
shared task ( to multiple
languages (English plus Catalan, Chinese, Czech, German,
Japanese and Spanish). The core task of (jointly) extracting
syntactic and semantic dependencies and the main evaluation
scheme and methodology remains unchanged, with several new
twists proposed to make the task interesting also for those
who have already taken part in the English-only task in
2008. Among the new features are compatible evaluation for
several languages and their comparison, comparison of time
and space complexity based on participants' input, and
learning curve comparison for languages with large datasets.

The data contents and format will be similar to the CoNLL
2008 shared task whenever possible, depending also on the
source treebanks being used. The shared task data will
thus have the following features:

 * The syntactic and semantic dependencies will be
   represented directly.
 * The contents of the datasets will allow for joint
   learning of both syntactic and semantic dependencies
   and their labeling.
 * Tools will be provided whenever possible to help with
   the dependency analysis of the languages involved.
 * The contents and format of the data will enable the
   participants to build on the previous CoNLL shared
   tasks on semantic labeling and dependency parsing.
 * The format of the non-English datasets will be
   identical in form and close to identical in content
   to the English data. Participants will be thus required
   to submit results for all the languages provided.

Shared Task Submissions

Participants are required to register at the task main
web page at http://ufal.mff.cuni.cz/conll2009-st. Watch
that page also for updated information about data formats,
availability of trial data etc. and most importantly, how
to upload system test data results for evaluation.

Participants will have the opportunity to submit their
system description and results achieved to a separate
track of the CoNLL 2009 conference.

Dates and deadlines

 * Registration of participants - January 5th
 * Release of a small trial data set - January 5th
 * Release of training and development data sets - January 19th
 * Release of test data - March 11th
 * Submission of test runs - March 18th
 * Submission of papers - March 30th
 * Notification of acceptance - April 8th
 * Camera-ready deadline - April 15th

Shared Task Organizers

Jan Hajic (chair)
Institute of Formal and Applied Linguistics
Charles University in Prague
hajic (at) ufal.mff.cuni.cz
 * Massimiliano Ciaramita, Google, Inc., Zurich (Switzerland)
 * Richard Johansson, Lund University (Sweden)
 * Daisuke Kawahara, NICT (Japan)
 * Maria Antonia Marti, University of Barcelona (Spain)
 * Lluis Marquez, Universitat Politecnica de Catalunya, Barcelona (Spain)
 * Adam Meyers, New York University (USA)
 * Joakim Nivre, Uppsala University (Sweden)
 * Sebastian Pado, Stanford University (USA)
 * Pavel Stranak, Charles University, Prague (Czech Republic)
 * Mihai Surdeanu, Stanford University (USA)
 * Nianwen (Bert) Xue, University of Colorado, Boulder (USA)
 * Yi Zhang, Saarland University, Saarbruecken (Germany)