2003 Conference on Empirical Methods in Natural Language Processing
                             (EMNLP 2003)                          

                              July 11-12
                            Sapporo, Japan

                      PRELIMINARY CALL FOR PAPERS

SIGDAT, the Association for Computational Linguistics' special
interest group on linguistic data and corpus-based approaches to NLP,
invites submissions to EMNLP 2003.  The conference will be held on
July 11-12 in Sapporo, Japan, immediately following the 41st meeting
of the ACL (ACL 2003).

CONFERENCE URL: 
http://www.ai.mit.edu/people/mcollins/emnlp03

We are interested in papers from academia, government, and industry on
all areas of traditional interest to the SIGDAT community and aligned
fields, including but not limited to:

- information extraction
- information retrieval
- language and dialogue modeling
- lexical acquisition
- machine translation
- multilingual technologies
- question answering
- statistical parsing
- summarization
- generation
- tagging
- term and named entity extraction
- word sense disambiguation
- word, term, and text segmentation
- general NLP-related machine learning techniques: 
          theory, methods and algorithms

In addition to providing a general forum, the theme for this year is

     "Combining Deep Analysis and Statistical Methods for NLP"

We solicit papers that describe attempts to apply statistical analysis
to "deeper" representations of natural language than existing methods.
Some illustrative examples are:

- Statistical processing of syntactic formalisms which give detailed
analyses, such as LFG, CCG, HPSG, or TAG.

- Extraction of logical form/predicate-argument structure, or
information extraction that goes beyond named entities to relations
between entities.

- Statistical approaches to dialogue systems.

- Statistical approaches to generation.

- Corpus-based approaches to machine translation which make use of
deeper analyses than the original IBM alignment models.

- Empirical and statistical work on Natural Language "Understanding".

- Work connecting statistical NLP to research in probabilistic
reasoning and representation in AI, for example reinforcement learning
and belief networks.


SUBMISSIONS
º
Submissions should take the form of full papers (up to 8 pages in
two-column format) describing original, unpublished work.  Papers
being submitted to other meetings must provide this information on the
title page.


MORE INFORMATION

will be coming soon; see also last year EMNLP's website.


IMPORTANT DATES (PRELIMINARY)

Submission deadline: April 4, 2003 
Acceptance notification: May 9, 2003 
Camera-ready copy due: June 6, 2003 
Conference: July 11-12, 2003 


CONFERENCE ORGANIZERS

Michael Collins (chair), 
MIT AI Lab, 
mcollins@ai.mit.edu

Mark Steedman (co-chair), 
University of Edinburgh,
steedman@informatics.ed.ac.uk


CONFERENCE URL: 
http://www.ai.mit.edu/people/mcollins/emnlp03