[Elsnet-list] COLING 2008 Information Retrieval for Question Answering (IR4QA) Workshop

Mark Greenwood mark at dcs.shef.ac.uk
Fri Feb 22 13:59:09 CET 2008

                          Call for Papers 

                         COLING'08 Workshop


                    August 2008, Manchester, UK

Open domain question answering (QA) has become a very active research
area over the past decade, due in large measure to the stimulus of the
TREC Question Answering track (now a track within the recently formed
Text Analysis Conference, TAC). This track addresses the task of
finding *answers* to natural language (NL) questions (e.g. "How
tall is the Eiffel Tower?" "Who is Aaron Copland?" "What effect
does second-hand smoke have on non-smokers?") from large text
collections. This task stands in contrast to the more conventional IR
task of retrieving *documents* relevant to a query, where the
query may be simply a collection of keywords (e.g. "Eiffel Tower",
"American composer, born Brooklyn NY 1900, ...").

Finding answers requires processing texts at a level of detail that
cannot be carried out at retrieval time for very large text
collections. This limitation has led many researchers to rely on,
broadly, a two stage approach to the QA task. In stage one a subset of
question-relevant texts are selected from the whole collection.  In stage
two this subset is subjected to detailed processing for answer
extraction. Clearly performance at stage two is bounded by performance
at stage one, and previous work has shown that, despite the
sophistication of standard IR ranking algorithms, they are not well
suited to the stage one task of retrieving relevant documents given
short natural language questions. It is likely that improvements in
this area will come from linguistic insights into why QA focused IR is
different from the traditional IR model. 

With the continued expansion of QA research into more complex question
types and with the speed with which answers are returned becoming an
issue, the importance of having good, QA-focused IR techniques is
likely to increase. To date this topic has received limited explicit
attention despite its obvious importance. This 2nd IR4QA workshop aims
to address this situation by continuing to attract the attention of
researchers to the specific IR challenges raised by QA.

For this workshop, we solicit papers that address any aspect of
QA-focussed IR, in order to improve overall system
performance. Possible topics include, but are not limited to: 
o parameterizations/optimizations of specific IR systems for QA
o studies of query formation strategies suited to QA, e.g. named
   entity pre-processing of questions
o different uses of IR for different question types (eg, factoid,
   list, definition, event, how, ...)
o utility of term matching constraints, e.g. term proximity, for QA
o analyses of differing IR techniques for QA
o impact of IR performance on overall QA performance
o QA-orientated corpus pre-processing, e.g. indexing POS tags,
   named entities, semantically-tagged entities, relationships, etc.
   rather than simply tokens
o evaluation measures for assessing IR for QA
o retrieval from semi-structured data - i.e. QA from Wikipedia

Important Dates

Paper Submission Deadline:  28th April
Notification of Acceptance: 6th June
Camera-Ready Papers Due:    1st July

Submission Instructions

Authors are invited to submit original, unpublished work on the topic
areas of the workshop. Submissions should follow the standard two
column formatting instructions for the main COLING 2008 conference.
Submitted papers should be no longer than eight (8) pages in length,
including references. We strongly recommend the use of the Latex and
Microsoft Word style files which are available from the main
conference website.

As reviewing will be blind, the paper should not include the authors'
names and affiliations. Furthermore, self-references that reveal the
author's identity, e.g., "We previously showed (Smith, 1991) ...",
should be avoided. Instead, use citations such as "Smith previously
showed (Smith, 1991) ...". 

Submission will be electronic. Details will appear on the workshop web
site (http://nlp.shef.ac.uk/ir4qa/2008/). 

Questions regarding the submission procedure should be directed to
Mark A. Greenwood (mark at dcs.shef.ac.uk). 

Workshop Organizers

Mark A. Greenwood
Department of Computer Science, University of Sheffield

Programme Committee Members

Matthew W. Bilotti    (Carnegie Mellon University)
Gosse Bouma           (University of Groningen)
Charles Clarke	    (University of Waterloo)
Hoa Dang              (NIST)
Robert Gaizauskas     (University of Sheffield)
Eduard Hovy           (ISI)
Jimmy Lin             (University of Maryland)
John Prager           (IBM)
Horacio Saggion       (University of Sheffield)
Jörg Tiedemann        (University of Groningen)
Bonnie Webber         (University of Edinburgh)
Ralph Weischedel      (BBN)

More information about the Elsnet-list mailing list