Home | Shared Task

Thirteenth Conference on Computational Natural Language Learning
Boulder, CO, USA
June 4-5
Second Call for Papers

CoNLL is the yearly international conference organized by SIGNLL (the
ACL Special Interest Group on Natural Language Learning). This year,
2009, CoNLL will be collocated with NAACL in Boulder, CO, USA.

We invite submission of papers about natural language learning topics,
including, but not limited to:

 * Computational models of human language acquisition

 * Computational models of the evolution of language

 * Machine learning methods applied to natural language processing
   tasks (speech processing, phonology, morphology, syntax,
   semantics, discourse processing, machine translation)

 * Statistical methods (Bayesian learning, log-linear models, kernel
   methods, graphical models)

 * 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

 * Learning architectures for structural and relational NLP tasks

 * Reinforcement learning

 * Active learning, ensemble methods, meta-learning

 * Computational learning theory analysis of language learning

 * Empirical and theoretical comparisons of language learning methods

 * Models of induction and analogy in linguistics

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

Special Topic of Interest

The field of natural language learning has made great strides over the
last 15 years, especially in the design and application of supervised
and batch learning methods.  However, two challenges arise with this
kind of approach.  First, in core NLP tasks, supervised approaches
require typically large amounts of manually annotated data, and
experience has shown that results often depend on the precise make-up
and genre of the training text, limiting generalizability of the
results and the reach of the annotation effort.  Second, in modeling
aspects of human language acquisition, the role of supervision in
learning must be carefully considered, given that children are not
provided explicit indications of linguistic distinctions, and
generally do not attend to explicit correction of their errors.
Moreover, batch methods, even in an unsupervised setting, cannot model
the actual online processes of child learning, which show gradual
development of linguistic knowledge and competence.

For our special focus this year at CoNLL, we invite papers on
unsupervised, minimally supervised and semi-supervised methods in
natural language learning, as well as on incremental learning
methods. Specifically, we encourage submissions of papers addressing:

 * Semi-supervised approaches that improve existing supervised
   methods by leveraging unlabeled data.

 * Learning methods and novel approaches to automatic annotation 
   that draw on a minimal amount of human supervision. 

 * Novel unsupervised models of human language learning, with special
   interest in incremental methods that can account for the
   time-course of acquisition data. 

 * Learning methods for NLP tasks that can adapt over time to new 
   inputs, and that increase robustness of existing approaches.

 * Connections between techniques from the cognitive modeling domain
   and NLP tasks that help to alleviate the training data bottleneck.

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 Czech, Chinese, Spanish, Catalan,
Japanese, and German). 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

 * 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 or
   close to identical to the English data, to encourage participants
   to run their systems on other languages as well.

The task is described in detail in its own Call for Participation at

Shared Task contact email: conll09st@ufal.mff.cuni.cz

Shared Task main dates and deadlines:

 * Release of training and development data sets: January 19th (passed)
 * Task running period (test data available): March 11th - 18th
 * Submission of system papers: March 30th
 * Camera-ready deadline: April 15th

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.

Invited Speakers

* Michael C. Frank
  Massachusetts Institute of Technology
  "Word learning through communicative inference"

* Andrew McCallum
  University of Massachusetts Amherst

Main Session Submissions

A paper submitted to CoNLL-2009 must describe original, unpublished
work. Submit a full paper of no more than 8+1 pages in PDF format by
March 4 2009, 23:59 GMT, electronically through the web form at

Only electronic submissions will be accepted.  Submissions should
follow the two-column format of NAACL HLT 2009 proceedings, and be at
most eight (8) pages in length. To encourage thorough citation of
related work, the references section does not count against the 8 page
limit: up to one additional page is allowed for the references section
of a submitted paper.  We strongly recommend the use of the NAACL HLT
2009 LaTeX style files or Microsoft Word Style files tailored for this
year's conference. Papers must conform to the official NAACL HLT 2009
style guidelines. Authors who cannot 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-2009. A paper that appears in CoNLL-2009 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 follow the NAACL HLT 2009 style
and are due April 15, 2009.  At least one author is expected to
register for the conference and present the paper.

Important Dates

 * Paper submission deadline:   March 4, 2009, 23:59 GMT
 * Notification of acceptance:  April 3
 * Camera-ready copy deadline:  April 15
 * Conference:                  June 4-5

Shared Task Submissions

See the shared task web page for detailed instructions at

Conference Organizers

Suzanne Stevenson
Department of Computer Science
University of Toronto
suzanne (at) cs.toronto.edu

Xavier Carreras
Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology
carreras (at) csail.mit.edu

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 Research (Switzerland)
* Richard Johansson, Lund University (Sweden)
* Daisuke Kawahara, NICT (Japan)
* Maria Antònia Martí, University of Barcelona (Spain)
* Lluís Màrquez, Technical University of Catalonia (Spain)
* Adam Meyers, New York University (USA)
* Joakim Nivre, Uppsala University (Sweden)
* Sebastian Padó, 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, Saarbrücken (Germany) 

Information Officer

Erik Tjong Kim Sang
University of Groningen (The Netherlands)
e.f.tjong.kim.sang (at) rug.nl

Program Committee

* Steven Abney, University of Michigan (USA)
* Afra Alishahi, Saarland University (Germany)
* Galen Andrew, Microsoft Research (USA)
* Giuseppe Attardi, University of Pisa (Italy)
* Kirk Baker, Collexis Inc (USA)
* Tim Baldwin, University of Melbourne (Australia)
* Roberto Basili, University of Roma Tor Vergata (Italy)
* Phil Blunsom, University of Edinburgh (UK)
* Antal van den Bosch, Tilburg University (The Netherlands)
* S.R.K. Branavan, Massachusetts Institute of Technology (USA)
* Chris Brew, Ohio State University (USA)
* Sabine Buchholz, Toshiba Research Europe Ltd. (UK)
* Paula Buttery, Cambridge University (UK)
* Claire Cardie, Cornell University (USA)
* Nicola Cancedda, Xerox Research Center Europe (France)
* Sander Canisius, Tilburg University (The Netherlands)
* Ming-Wei Chang, University of Illinois at Urbana-Champaign (USA)
* Ciprian Chelba, Google Research (USA)
* Colin Cherry, Microsoft Research (USA)
* Massimiliano Ciaramita, Google Research (Switzerland)
* Alexander Clark, Royal Holloway, University of London (UK)
* James Clarke, University of Illinois at Urbana-Champaign (USA)
* Stephen Clark, Oxford University (UK)
* Michael Collins, Massachusetts Institute of Technology (USA)
* Paul Cook, University of Toronto (Canada)
* James Cussens, University of York (UK) 
* Walter Daelemans, University of Antwerp (Belgium)
* Hal Daumé III, University of Utah (USA)
* Jacob Eisenstein, University of Illinois at Urbana-Champaign (USA)
* Katrin Erk, University of Texas at Austin (USA)
* Anna Feldman, Montclair State University (USA)
* Jenny Finkel, Stanford University (USA)
* Radu Florian, IBM research (USA)
* Dayne Freitag, HNC Software (USA)
* Pascale Fung, Hong Kong University of Science and Technology (Hong Kong)
* Michel Galley, Stanford University (USA)
* Daniel Gildea, University of Rochester (USA)
* Roxana Girju, University of Illinois at Urbana-Champaign (USA)
* John Hale, Michigan State University (USA)
* James Henderson, University of Geneva (Switzerland)
* Julia Hockenmaier, University of Illinois at Urbana-Champaign (USA)
* Liang Huang, Google Research (USA)
* Richard Johansson, Lund University (Sweden)
* Rie Johnson, RJ Research Consulting (USA)
* Rohit Kate, University of Texas at Austin (USA)
* Philipp Koehn, University of Edinburgh (UK)
* Rob Koeling, Sussex University (UK)
* Terry Koo, Massachusetts Institute of Technology (USA)
* Anna Korhonen, Cambridge University (UK)
* Shalom Lappin, King's College, London (UK)
* Dekang Lin, Google Research (USA)
* Xiaofei Lu, Pennsylvania State University (USA)
* Rob Malouf, San Diego State University (USA)
* Lluís Màrquez, Technical University of Catalonia (Spain)
* Yuji Matsumoto, Nara Institute of Science and Technology (Japan)
* Diana McCarthy, Sussex University (UK)
* Ryan McDonald, Google Research (USA)
* Paola Merlo, University of Geneva (Switzerland)
* Rada Mihalcea, University of North Texas (USA)
* Saif Mohammad, University of Maryland (USA)
* Alessandro Moschitti, DISI, University of Trento (Italy)
* Gabriele Musillo, University of Geneva (Switzerland)
* John Nerbonne, University of Groningen (The Netherlands)
* Hwee Tou Ng, National University of Singapore (Singapore)
* Vincent Ng, University of Texas at Dallas (USA)
* Grace Ngai, The Hong Kong Polytechnic University (Hong Kong)
* Joakim Nivre, Uppsala University and Växjö University (Sweden)
* Franz Och, Google Research (USA)
* Miles Osborne, University of Edinburgh (UK)
* Chris Parisien, University of Toronto (Canada)
* Ted Pedersen, University of Minnesota (USA)
* Slav Petrov, UC Berkeley (USA)
* David Powers, Flinders University (Australia)
* Chris Quirk, Microsoft Research (USA)
* Ari Rappoport, Hebrew University (Israel)
* Lev Ratinov, University of Illinois at Urbana-Champaign (USA)
* Sebastian Riedel, University of Edinburgh (UK)
* Brian Roark, Oregon Health & Science University (USA)
* Dan Roth, University of Illinois at Urbana-Champaign (USA)
* William Sakas, City University of New York (USA)
* Sabine Schulte im Walde, University of Stuttgart (Germany)
* Libin Shen, BBN Technologies (USA)
* David Smith, Johns Hopkins University (USA)
* Noah Smith, Carneggie Mellon University (USA)
* Ben Snyder, Massachusetts Institute of Technology (USA)
* Caroline Sporleder, Saarland University (Germany)
* Richard Sproat, University of Illinois at Urbana-Champaign (USA)
* Mihai Surdeanu, Stanford University (USA)
* Erik Tjong Kim Sang, University of Groningen (The Netherlands)
* Ivan Titov, University of Illinois at Urbana Champaign (USA)
* Vivian Tsang, University of Toronto (Canada)
* Aline Villavicencio, Federal University of Rio Grande do Sul (Brazil)
* Scott Wen-tau Yih, Microsoft Research (USA)
* Charles Yang, University of Pennsylvania (USA)
* Deniz Yuret, Koc University (Turkey)
* Luke Zettlemoyer, Massachusetts Institute of Technology (USA)