Fourth Computational Natural Language Learning Workshop
CoNLL-2000

CoNLL is the yearly workshop organized by SIGNLL, the Association for Computational Linguistics Special Interest Group on Natural Language Learning.

The meeting will be held in conjunction with ICGI-2000, the International Conference on Grammar Inference (http://vinci.inesc.pt/icgi-2000/) and the Learning Language in Logic workshop (http://www.lri.fr/~cn/LLL-2000/) in Lisbon on Thursday, September 14, 2000, and will feature a shared task competition about learning of chunking. There will be joint sessions with ICGI-2000 and the LLL workshop on topics of common interest. Previous CoNLL meetings were held in Madrid, Sydney, and Bergen.

We invite submissions of abstracts on all aspects of computational natural language learning, including

• Computational models of human language acquisition
• Computational models of the origins and 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 analyses of language learning
• Empirical and theoretical comparisons of language learning methods
• Models of induction and analogy in Linguistics

A special session of the workshop will be devoted to a shared task: the identification of phrases (syntactic constituents) with machine learning methods, a task called chunking.

Format for paper submissions:

Submit an abstract of maximum 1500 words by May 22, 2000 electronically to the address below (postscript or ascii). Authors of accepted abstracts will be invited to produce a full paper to be published in the proceedings of the workshop, which will be available at the workshop for participants, and distributed afterwards by the ACL.

Format for shared task submissions:

Submit an abstract of maximum 1500 words describing the learning approach, and your solution to the test set by May 22, 2000 to the address below (preferably by email). 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 Abstract Submission: May 22, 2000
Deadline for Shared Task Submission: May 22, 2000
Notification: June 15, 2000
Deadline Full paper submission: July 31, 2000
Workshop: September 14, 2000

Programme Committee (SIGNLL Board)

Claire Cardie (Cornell) (co-chair)
Walter Daelemans (Antwerp) (co-chair)
Erik Tjong Kim Sang (Antwerp) (co-chair, shared task coordinator)

Antal van den Bosch (Tilburg, Netherlands)
Thorsten Brants (Saarbruecken, Germany)
Michael Brent (Saint Louis, USA)
James Cussens (York, UK)
Raymond Mooney (Austin, USA)
John Nerbonne (Groningen, Netherlands)
Miles Osborne (Edinburgh, UK)
David Powers (Adelaide, Australia)
Ronan Reilly (Dublin, Ireland)

Invited Speaker:

Dan Roth (University of Illinois at Urbana-Champaign, USA)

Address:

Submit paper abstracts to:

Walter Daelemans
CNTS Language Technology group
UIA - GERMAANSE
Universiteitsplein 1
B-2610 Antwerpen
BELGIUM
walter.daelemans@uia.ua.ac.be

Submit shared task submissions to:

Erik Tjong Kim Sang
CNTS Language Technology group
UIA - GERMAANSE
Universiteitsplein 1
B-2610 Antwerpen
BELGIUM
erikt@uia.ua.ac.be