OPEN DOMAIN QUESTION ANSWERING
INVITED SPEAKER:
John Prange, ARDA
PANEL: The Future of Q/A
PANELISTS:
Sanda Harabagiu, SMU
Donna Harman, NIST
John Prange, ARDA
Yael Ravin, IBM
PROGRAM ORGANIZERS:
Yael Ravin, IBM
John Prager, IBM
Sanda Harabagiu, SMU
PROGRAM COMMITTEE:
Jamie Callan, CMU
Jaime Carbonell, CMU
Donna Harman, NIST
Graeme Hirst, Toronto
Jerry Hobbs, SRI
Christian Jacquemin, LIMSI
Liz Liddy, Syracuse
Marc Light, MITRE
Dekang Lin, Alberta
Steve Maiorano, AAT
Dan Moldovan, SMU
Dragomir Radev, Michigan
Tomek Strzalkowski, SUNY Albany
Ellen Voorhees, NIST
PREFACE
Open-domain question answering (QA) represents a new challenge to both commercial applications
and academic research. When users have specific questions, such as ”What countries did Clinton
visit in 1999?” or ”How much does a ThinkPad cost?”, they would like to see one (or a few)
succinct answer(s). This workshop focuses on technical issues that directly apply to this challenge,
and, in particular, on theoretical and pragmatic issues involved in the creation, evaluation and
implementation of QA techniques. We concentrate on QA that is automatic and either domain
independent or working within a large open domain, such as news or technical support.
To accommodate this need for automatically finding answers to open-domain questions, several
different fields of research come together - information retrieval, natural-language processing
and knowledge representation. This workshop provides a forum for discussions of QA as the
combination and integration of techniques from these three fields. The papers in this volume discuss
QA topics such as question analysis and answer selection; logical formalisms for representing QA
semantics; new sources of knowledge, such as the Web; and tools for evaluating the results of QA.
The invited talk, represented here by its abstract, examines future directions in this field.
