*********************************************************************

                            ACL'99 Workshop

                     COREFERENCE AND ITS APPLICATIONS

                             June 22, 1999

                         University of Maryland

                         College Park, MD.  USA

                 http://www.cs.duke.edu/~amit/acl99-wkshp.html


WORKSHOP DESCRIPTION 


Coreference is in some sense nature's own hyperlink. It conveys how
individual statements are connected within documents, across documents
and across bodies of human knowledge. Consequently coreference
resolution algorithms are at the core of Natural Language
Processing. Most of the work done on coreference deals with
a single language and a single text document (usually newswire).

As NLP research matures into "application" phases (as opposed to
theory-development), NLP systems are moving beyond traditional
research sources to document sets which reflect a more natural, 
research-oriented mix.  This shift can be seen in both the document 
sets and tasks used in recent HUB, MET, and TDT evaluations.  The
new sources consist of documents in several different languages, 
documents with data from noisy sources, and documents containing 
multimedia.  In order for NLP systems to make a successful
transition to these new sources, it is critical for coreference 
resolution systems to also work on these new sources.

The workshop invites papers regarding the theory, design, and
evaluation of coreference resolution systems that deal with
non-traditional data sources.  In particular, we encourage 
submission of papers for the following types of coreference:

    *-Cross-document coreference

    *-Coreference resolution in languages other than English

    *-Coreference resolution on noisy data

    *-Coreference resolution on non-text data (example: human speech)

    *-Coreference resolution on multimedia data

In addition, the workshop also invites papers on innovative NLP
applications that rely heavily on coreference resolution systems.

FORMAT FOR SUBMISSION

Paper submissions should consist of a full paper (5000 words or less,
including references).  Each submission should include a separate
title page providing the following information: the title, a short
abstract, names and affiliations of all the authors, the full address
of the primary author (or alternate contact person), including phone,
fax, and email.

Papers may be submitted by submitting three hard copies to:

Amit Bagga
General Electric CRD 
Room K1-5C38B
1 Research Circle
Niskayuna, NY
12309.  USA

phone: 1-518-387-7077

email: bagga@crd.ge.com

IMPORTANT DATES

Paper submission deadline:      March 29

Notification of acceptance:     April 16

Camera ready papers due:        April 30

ORGANIZATION COMMITTEE
Co-Chairs:

Amit Bagga (Contact Person) 
General Electric Corporate
Research and Development 
K1-5C38B 
1 Research Circle
Niskayuna, NY 12309.  USA

bagga@crd.ge.com
518-387-7077 (voice)
518-387-6845 (fax)

Breck Baldwin 
Institute for Research in Cognitive Science
University of Pennsylvania 
3401 Walnut Street, #400C 
Philadelphia, PA 19104.  USA

breck@linc.cis.upenn.edu 

Sara J. Shelton 
US Department of Defense 
9800 Savage Road, E24 
Ft Meade, MD 20755. USA 

PROGRAM COMMITTEE

Amit Bagga - GE CRD 
Breck Baldwin - University of Pennsylvania 
Branimir Boguraev - IBM T.J. Watson Research Center 
Ed Hovy - Information Sciences Institute (USC/ISI) 
Mark T. Maybury - MITRE 
Ruslan Mitkov - University of Wolverhampton 
Sara Shelton - DoD