2002 Conference on Empirical Methods in NLP--Preliminary CFP

[Priscilla Rasmussen]

************************************************************************
              2002 Conference on Empirical Methods
                 in Natural Language Processing
                          (EMNLP 2002)

                  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 2002.  The conference will be held at
University of Pennsylvania, Philadelphia, PA, USA on July 6-7,
immediately preceding the anniversary 40th meeting of the ACL (ACL
2002).

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 dialog modeling
- lexical acquisition
- machine translation
- multilingual technologies
- question answering
- statistical parsing
- summarization
- tagging
- term and named entity extraction
- word sense disambiguation
- word, term, and text segmentation
- general NLP-related machine learning techniques:=20
          theory, methods and algorithms
          (incl. text mining, smoothing, etc.)

As a follow-up to last year's focus on analyzing the current "Successes
and Challenges" in the corpus-based methods, we encourage submissions=20
on the theme=20

                 "The Next Big Thing in Data-driven NLP"

We solicit papers that describe attempts to substantially and
radically deviate from current practice of simple adaptations of
existing and usually well-studied methods. All directions of a venture
to a territory previously unknown (or once abandoned for one reason or
another) to NLP are welcome, such as but not limited to

- using Really Large Corpora (cf. last year's Brill's talk);
- using previously neglected methods, including those from non-NLP=20
  fields, such as biology, nuclear physics, or finance, with promising=20
  results and/or reasonable potential for the future;
- employing known methods in a radically different way or on
  problems they were not tried upon previously, with truly significant
  improvement;
- combining intuition-based and data-based methods (finally!) with=20
  substantially improved results on known problems.

We stress though that such papers, however radical their content might
be, stick to the usual practice of documenting the results using
standard experimental and evaluation practice. That does not exclude
that authors provide extended final section in their submissions,
discussing perhaps even slightly speculatively what the future might
look like.

Submissions:

Submissions should take the form of full papers (3200 words or less,
excluding references) describing original, unpublished work.  Papers
being submitted to other meetings must provide this information on the
title page.

More info will be coming soon; see also last year EMNLP's website at
http://www.cs.cornell.edu/home/llee/emnlp.html

Important Dates:

Submission deadline: April 4, 2002=20
Acceptance notification: May 8, 2002=20
Camera-ready copy due: June 6, 2002=20
Conference: July 6-7, 2002=20

Conference Organizers:

- Jan Hajic (chair), Charles University, Prague, Czech Republic
  (hajic at ufal.mff.cuni.cz)=20
- Yuji Matsumoto (co-chair), Nara Institute of Science and Technology
  (matsu at is.aist-nara.ac.jp)

Conference URL http://ufal.mff.cuni.cz/~hajic/emnlp02