The Conference on Empirical Methods in Natural Language
Processing will be held in conjunction with the 50th Anniversary
celebration of the Eniac Computer, taking place at the University of
Pennsylvania May 17-18, 1996. In the spirit of SIGDAT events, this
conference will offer a general forum for novel research in
corpus-based and statistical natural language processing.
Areas of interest include (but are not limited to): automatic
linguistic annotation of text (eg. phrase structure, word senses,
parts of speech), language modelling, machine translation, spelling
correction and lexicography. In addition to providing a general
forum, the conference will be centered around the following theme:
Algorithm or Representation?
Many novel approaches to empirical natural language processing have
been developed recently. How much of a method's success is due to the
particular algorithm used, and how much to the richness and
appropriateness of the feature set? Is it true that diverse
algorithms tend to perform roughly the same given the same training
data and feature set? Where are the greatest benefits to be found: in
refining the representation, enhancing the algorithm or increasing the
training set size? Papers providing quantitative comparisons are
especially welcome.
We encourage submission of papers addressing this topic, as well as
papers describing strengths, weaknesses, and advances in the areas of
algorithms and representations appropriate for corpus-based natural
language processing. However the conference will be diverse in scope
and all innovative papers on empirical methods in NLP will be welcome.
PROGRAM CHAIR: Eric Brill, Johns Hopkins University
and co-chair: Ken Church, AT&T Bell Laboratories
SPONSORS: Department of Computer and Information Science,
University of Pennsylvania.
Lexis-Nexis, a Division of Reed Elsevier, Inc.
SIGDAT, a special interest group of the ACL.
SCHEDULE: Submission Deadline: February 20
Notification of Acceptance: March 18
Camera-ready Final Papers: April 15
Conference Dates: May 17-18
FORMAT FOR SUBMISSION: Authors should submit a full-length paper
(3500-8000 words) either electronically or in hard-copy.
Electronic submissions must either be plain ascii text or
a single latex file. Hard copy submissions should include
six (6) copies of the paper. Please be sure to include
your e-mail address on your paper. Unless requested
otherwise, notification of acceptance will be sent electronically
to the first author.
A paper accepted for presentation at this conference
cannot be presented or have been presented at any other meeting
with publicly available proceedings. Papers that are being
submitted to other conferences must include notification of this
fact with the submission.
CONTACT AND ADDRESS FOR SUBMISSION:
Eric Brill: EMNLP Conference
Department of Computer Science
3400 N. Charles St. Room 224 NEB
Johns Hopkins University
Baltimore, Md. 21218-2694
http://www.cs.jhu.edu/faculty/brill/Conf_on_Emp_Meth.html
SigDat Home Page: http://www.cis.upenn.edu/~yarowsky/sigdat.html
PROGRAM COMMITTEE:
Claire Cardie, Cornell University
Eugene Charniak, Brown University
Yuqing Gao, IBM
Marti Hearst, Xerox PARC
Gunnel Kallgren, Stockholm University
Raymond J. Mooney, University of Texas, Austin
Yoshinori Sagisaka, ATR
Geoffrey Sampson, Sussex University
David Yarowsky, Johns Hopkins University
Joe Zhou, Lexis-Nexis
REGISTRATION INFORMATION: Will be posted shortly.
NOTE: This conference will be complementary to the Fourth Workshop on
Very Large Corpora (http://www.ling.umu.se/SIGDAT/WVLC-4.html), being
held at COLING-96 in Copenhagen on August 4, 1996.
For information on other events being held in conjunction with the
50th anniversary of the ENIAC computer, see:
http://homepage.seas.upenn.edu/~museum/
For information on visiting Philadelphia, see:
http://www.libertynet.org/phila-visitor