First Call for Papers CoNLL-2004: Eighth Conference on Computational Natural Language Learning Organized at HLT/NAACL 2004, Boston, MA, USA May 6-7, 2004 CoNLL is an international conference for discussion and presentation of research on natural language learning. 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, language engineering applications) - 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) - Statistical methods (Bayesian Learning, HMM, maximum entropy, SNoW, Support Vector Machines) - 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 We encourage the submission of papers combining (statistical) machine learning with symbolic knowledge sources. CoNLL is the yearly conference organized by SIGNLL, the Association for Computational Linguistics Special Interest Group on Natural Language Learning. Previous CoNLL meetings were held in Madrid (1997), Sydney (1998), Bergen (1999), Lisbon (2000), Toulouse (2001), Taipei (2002), and Edmonton (2003). See http://www.aclweb.org/signll/ and = http://ilk.uvt.nl/~signll/conll.html for more information about SIGNLL and CoNLL. Shared Task This year's conference will also accept submissions for a shared task: machine learning approaches to automatic labeling of semantic roles. Participant groups will use the same training and testing material, and the evaluation will be done according to fixed criteria, thus allowing comparison between various learning strategies. More information on the shared task is available at the shared task web page: http://cnts.uia.ac.be/conll2004/roles/ Invited Speaker To be announced later. Submissions Main Session Submissions A paper submitted to CoNLL-2004 must describe original, unpublished work. Submit a full paper of no more than 8 pages in PDF format by Feb 4, 2004 electronically to the email address conll04@comp.nus.edu.sg. The subject line of the email message should be "CoNLL-2004 submission", with the PDF paper as an attachment file. Only email submissions will be accepted. The submitted paper should be in two column format and follow the ACL style. 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 email message body, include 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-2004. A paper that appears in CoNLL-2004 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 ACL style and are due Mar 15, 2004. Shared Task Submissions Submit a paper of maximum 4 pages describing the learning approach, and your results on the development set by Feb 23, 2004 to the email address conll04st@lsi.upc.es (see the shared task web page for concrete formats and styles). A special section of the proceedings will be devoted to a comparison and analysis of the results and to a description of the approaches used. Important Dates Deadline for main session paper submission: Feb 4, 2004 Deadline for shared task submission: Feb 23, 2004 Notification of acceptance: Mar 1, 2004 Deadline for camera-ready papers: Mar 15, 2004 Conference: May 6-7, 2004 Conference Organizers Hwee Tou Ng Department of Computer Science School of Computing National University of Singapore 3 Science Drive 2 Singapore 117543 Email: nght@comp.nus.edu.sg and Ellen Riloff School of Computing University of Utah 50 S. Central Campus Drive, RM 3190 MEB Salt Lake City, UT 84112-9205 USA Email: riloff@cs.utah.edu Shared Task Organizers Xavier Carreras and Lluis Marquez Software Department (LSI), Technical University of Catalonia (UPC, Campus Nord). Jordi Girona Salgado 1-3 Barcelona E-08034, Catalonia Spain Email: {carreras,lluism}@lsi.upc.es Program Committee (Partial list) Hwee Tou Ng, National University of Singapore (Singapore), co-chair Ellen Riloff, University of Utah (USA), co-chair Xavier Carreras, UPC (Spain), shared task co-chair Lluis Marquez, UPC (Spain), shared task co-chair Thorsten Brants, Google Inc (USA) Claire Cardie, Cornell University (USA) James Cussens, University of York (UK) Walter Daelemans, University of Antwerp (Belgium) Ido Dagan, Bar Ilan University / LingoMotors (Israel) Diane Litman, University of Pittsburgh (USA) Yuji Matsumoto, Nara Institute of Science and Technology (Japan) Rada Mihalcea, University of North Texas (USA) Raymond Mooney, University of Texas at Austin (USA) John Nerbonne, University of Groningen (Netherlands) Grace Ngai, Hong Kong Polytechnic University (Hong Kong) Miles Osborne, University of Edinburgh (UK) David Powers, Flinders University (Australia) Adwait Ratnaparkhi, Microsoft (USA) Dan Roth, University of Illinois at Urbana-Champaign (USA) Erik Tjong Kim Sang, University of Antwerp (Belgium) Antal van den Bosch, Tilburg University (Netherlands) The program committee will be expanded to include additional members.