THIRD CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING
Sponsored by SIGDAT (ACL's Special Interest Group for Linguistic Data and Corpus-based Approaches to NLP)

Tuesday, June 2, 1998
Granada, Spain


Following the
First International Conference on Language Resources and Evaluation
and the
NSF Workshop on Translingual Information Management


In the spirit of SIGDAT events, this conference offers a general forum for novel research in corpus-based and statistical natural language processing. This year's conference is focused on work that describes and evaluates the strengths, weaknesses, and recent advances in corpus-based NLP as applied to multi-lingual applications.

The development of natural language applications which handle multi-lingual information is the next major challenge facing the field of computational linguistics. How well do techniques for lexical tagging, parsing, anaphora resolution, etc., handle the specific problems of multi-lingual applications? What new methods have been developed to address the deficiencies of existing algorithms for these tasks or to address problems specific to handling multi-lingual applications? What problems still lack an adequate empirical solution? Conversely, how can data-driven NLP methods be improved with the help of multi-lingual data?

For additional information, contact the conference organizers directly at emnlp3@cs.vassar.edu.



Program chairs

Nancy Ide (chair)
Department of Computer Science
Vassar College
124 Raymond Avenue
Poughkeepsie, New York 12604-0520 USA
Tel: (+1 914) 437 5988
Fax: (+1 914) 437 7498
E-mail: ide@cs.vassar.edu

Atro Voutilainen (co-chair)
Research Unit for Multilingual Language Technology
Department of General Linguistics
P.O. Box 4 (Keskuskatu 8, 7th floor)
FIN-00014 University of Helsinki
Finland
Tel: (+358 9) 191 23 507
Fax: (+358 9) 191 23 598
E-mail: atro.voutilainen@ling.helsinki.fi

Program Committee


Last modification : 4/15/98