SPONSOR:
CLIF (Computational Linguistics in Flanders)
INVITED SPEAKERS:
Eric Brill, Microsoft Research
John Nerbonne, University of Groningen
PROGRAM COMMITTEE:
Walter Daelemans, University of Antwerp and Tilburg University, Chair
R´emi Zajac, New Mexico State University, Chair
Thorsten Brants, Xerox PARC
Michael Brent, Washington University in Saint Louis
Claire Cardie, Cornell University
James Cussens, University of York
Herv´e D´ejean, University of Tuebingen, Shared Task coordinator
Gregory Grefenstette, Xerox Grenoble
Raymond Mooney, University of Texas at Austin
John Nerbonne, Groningen University
Kemal Oflazer, Sabanci University
Miles Osborne, University of Edinburgh
David Powers, Flinders University
Ronan Reilly, University College Dublin
Dan Roth, University of Illinois at Urbana-Champaign
Erik Tjong Kim Sang, University of Antwerp, Shared Task coordinator
Antal van den Bosch, Tilburg University
Yorick Wilks, University of Sheffield
CONFERENCE WEBSITE:
http://lcg-www.uia.ac.be/conll2001/
PREFACE
This volume contains the papers accepted for presentation at the 2001 workshop on
Computational Natural Language Learning (CoNLL-2001), a SIGNLL meeting held in Toulouse,
France, July 6 and 7 in conjunction with the International and the European Conferences of the
ACL.
CoNLL-2001 is the fifth in a series of meetings organized by SIGNLL a0 , the ACL special
interest group on natural language learning. The CoNLL meeting is intended to address all aspects
of computational natural language learning, including those that are not regularly discussed at
computational linguistics meetings, such as computational models of human language acquisition,
computational models of the origins and evolution of language, biologically-inspired learning
methods etc.
This year, we have a special theme on learning mechanisms for the automated acquisition of
language resources (dictionaries, ontologies, grammars) or the automated adaptation of natural
language resources/processors to new domains or languages. The dimensions of learning that are
of interest include the integration of humans/linguists in the learning process, the structure of the
training data (especially, minimization of the training set), and the kind of knowledge that is learned.
This year’s CoNLL also features two invited presentations, one by Eric Brill on whether the web
changes empirical NLP, and one by John Nerbonne on the results of a successful European project
on Learning Computational Grammars. As in the previous two editions of CoNLL, we have a
shared task session, coordinated by Erik Tjong Kim Sang and Herv´e D´ejean. For this session,
training and test data were made available, and researchers were invited to apply their learning
system to this task. This year the task is clause identification. Six systems have participated, five
from Europe and one from Australia. You will find descriptions of these systems and their results
in this proceedings.
Of the 61 papers submitted, the programme committee selected 20 papers, representative of the
state of the art in computational language learning today. We are very grateful to our programme
committee for the effort they put in reviewing the papers. We are also grateful to the ACL/EACL-
2001 conference organizers on whom we could rely for the local organization. Finally, we most
gratefully acknowledge the support of our sponsor, the Computational Linguistics in Flanders
research community (CLIF) for sponsoring one of the invited speakers.
Walter Daelemans & R´emi Zajac (editors)
May 2001
a1 http://www.aclweb.org/signll/
