The Association for Computational Linguistics (ACL) and its special
interest group for linguistic data and corpus-based approaches to
NLP (SIGDAT) are organizing the
FOURTH WORKSHOP ON VERY LARGE CORPORA (WVLC-4)
WHEN: August 4, 1996 - in conjunction with COLING 96
(Turorials: Aug 2-3, Main conference: Aug 5-9, 1996).
WHERE: University of Copenhagen, Copenhagen, Denmark.
WORKSHOP DESCRIPTION:
This workshop, like preceding ones in the series, will offer an
international and general forum for the presentation of new advances
and applications in the area of large scale, corpus-based natural
language processing.
The fourth workshop will focus on the theme of:
Innovative uses and applications of large corpora
Large corpora, i.e. corpora ranging anywhere from 10^4 to 10^9 words, are
coming into existence for several different languages, and techniques for
analyzing them are improving. How are these resources actually being used?
The workshop encourages contributions that show innovative applications of
corpus-based NLP to problems of practical industrial importance.
The theme will provide an organizing structure to the workshop, and offer
a focus for discussion and debate between researchers and industrialists.
We also expect and will welcome a diverse set of submissions in all areas
of statistical and corpus-based NLP, including (but not limited to)
Text Analysis Techniques:
- robust parsing
- part of speech tagging
- term and name identification
- morphological analysis
- alignment of parallel texts and bilingual terminology
- sense disambiguation
- anaphora resolution
- event categorization
- discourse structure
Applications:
- Information Retrieval
- Lexicography
- Machine Translation
- Spelling and Grammar Correction
- Recognition: Speech, OCR, handwriting, etc.
PROGRAM CHAIRS:
Eva Ejerhed - University of Umea, Umea, Sweden
Ido Dagan - Bar Ilan University, Ramat Gan, Israel
FORMAT FOR SUBMISSION: Authors should submit a full length paper
(3500 - 8000 words), either electronically or in hard copy. Electronic
submissions should be mailed to "WVLC-4@ling.umu.se" and must be
either (a) a plain ascii text, (b) a single postscript file, or
(c) a single LaTex file (no separate figures or .bib files), following
the COLING 96 stylesheet, which is retrievable by anonymous ftp from
ling.umu.se, /pub/SIGDAT/colsub.sty. A model submission is provided
in /pub/SIGDAT/modelsub.tex. Hard copy submissions should be mailed
to Ido Dagan (address below), and should include four (4) copies of
the paper.
REQUIREMENTS: Papers should describe original work. A paper accepted
for presentation cannot be presented or have been presented at any other
meeting. Papers submitted to other conferences will be considered, as
long as this fact is clearly indicated in the submission.
SCHEDULE:
Submission Deadline: February 23, 1996
Notification Date: March 26, 1996
Camera ready copy due: April 26, 1996
The camera ready hard copies of final papers, prepared in a double
column format and laser printed, should be air-mailed to Eva Ejerhed
(address below) and must be received by April 26, 1996.
CONTACT:
Eva Ejerhed Ido Dagan
Dept of Linguistics, DGL Dept of Mathematics & Computer Science
University of Umea Bar Ilan University
S 90187 Umea, Sweden Ramat Gan 52900, Israel
e-mail: WVLC-4@ling.umu.se e-mail: dagan@bimacs.cs.biu.ac.il
http://www.ling.umu.se/SIGDAT/WVLC-4.html