CALL FOR PAPERS

Workshop on Pragmatics of Question Answering

May 6-7, 2004, Boston,
    held as an HLT/NAACL2004 conference workshop


WEB SITES
.......................................................
Workshop: http://languagecomputer.com/hltnaacl04qa
Main conference: www.hlt-naacl04.org

.....................................................................
DESCRIPTION

Research in Open-domain Question Answering (QA) has made substantial
advances in the past few years. Answering factual questions is
performed with better and better accuracy; multiple forms of
definition questions are processed correctly, and list questions
retrieve sequences of answers with good recall from large text
collections. Evaluations in the Text REtrieval Conference (TREC) QA
track, as well as ARDA's Advanced Question Answering for Intelligence
(AQUAINT) program, enable these advances in QA. These results and some
of the research that made them possible were discussed in various
workshops on QA topics organized at ACL (2001 and 2003), COLING
(2002), LREC (2002), EACL (2003) and the AAAI Spring Symposium series
(2002 and 2003). In the past year, with the emergence of
scenario-based questions, several forms of pragmatic processing have
started to influence the architecture of QA systems. The processing
requires multiple interactions with a QA system in the context of a
given scenario. Questions need to be decomposed in the context of the
scenario. Furthermore, context plays an important role in interaction
with the user background. These are just a few of the new features
required in QA systems processing complex questions.

This workshop will be a forum for researchers to discuss and present
their results in the new area of QA that moves beyond fact-seeking
into resolving complex questions. The topics that will be discussed
are:

    * semantics of scenario-based QA
    * dialogs for answering complex questions
    * ontological commitments imposed by QA scenarios
    * answering questions in context
    * multi-modal QA
    * processing negation, temporality and scoping in QA
    * abductive reasoning in QA
    * deep semantic representations and probabilistic reasoning
    * user background and its interactions with complex scenarios and QA 

A highlight of the workshop is the keynote speech.
_________________________________________________________________________
KEYNOTE SPEAKER: Dr. John Prange, Director of the AQUAINT Program, ARDA
________________________________________________________________________
PAPER SUBMISSION

Submissions should describe original, unpublished work. Papers are
limited to 8 pages. Submissions should use the style files available
on the main HLT/NAACL2004 conference web site. No author information
should be included in the papers since reviewing will be blind. Papers
not conforming to these requirements are subject to rejection without
review.

Submissions should be sent electronically (pdf or postscript) to
finley@languagecomputer.com. Submissions consist of (1) the paper; and
(2) a separate id page including the title, authors, a short abstract,
and a set of relevant keywords. The subject line should be "HLT/NAACL
QA paper submission" for paper submissions, and "HLT/NAACL QA id page"
for id page submission.

ORGANIZERS

Sanda Harabagiu, University of Texas at Dallas (sanda@cs.utdallas.edu)
Finley Lacatusu, Language Computer Corporation 
(finley@languagecomputer.com)

.......................................................................
IMPORTANT DATES

Paper submission deadline: 	January 9
Notification of acceptance: 	February 2
Camera ready papers due: 	February 20
Workshop dates:			May 6-7

......................................................................
PROGRAM COMMITTEE

Stefano Bertolo			Cycorp
Vasileios Hatzivassiloglou 	Columbia University
Eduard Hovy			USC/Information Sciences Institute
Elisabeth Liddy			Syracuse University
Steve Maiorano			ATP
Christopher Manning		Stanford University
Daniel Marcu			USC/Information Sciences Institute
Mark Maybury			MITRE
Dan Moldovan			Language Computer Corporation
Srini Narayanan			ICSI Berkeley
Hwee Tou Ng			National University of Singapore
John Prager			IBM
Tomek Strzalkowski		University at Albany
Ellen Voorhees			NIST
Jinxi Xu			BBN