Towards answer extraction

an application to technical domains

Fabio Rinaldi, James Dowdall, Michael Hess, Diego Molla, R Schwitter

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contribution

4 Downloads (Pure)

Abstract

The shortcomings of traditional Information Retrieval are most evident when users require exact information rather than relevant documents. This practical need is pushing the research community towards systems that can exactly pinpoint those parts of documents that contain the information requested. Answer Extraction (AE) systems aim to satisfy this need. This paper presents one such system (ExtrAns) which works by transforming documents and queries into a semantic representation called Minimal Logical Form (MLF) and derives the answers by logical proof from the documents. MLFs use underspecification to overcome the problems associated with a complete semantic representation and offer the possibility of monotonic, non-destructive extension.

Original languageEnglish
Title of host publicationECAI 2002: 15th European Conference on Artificial Intelligence, proceedings
EditorsFrank Van Harmelen
Place of PublicationAmsterdam, Netherlands
PublisherIOS Press
Pages460-464
Number of pages5
ISBN (Print)1586032577
Publication statusPublished - 2002
Event15th European Conference on Artificial Intelligence - LYON, France
Duration: 21 Jul 200226 Jul 2002

Publication series

NameFrontiers in Artificial Intelligence and Applications
PublisherIOS PRESS
Volume77
ISSN (Print)0922-6389

Conference

Conference15th European Conference on Artificial Intelligence
CountryFrance
CityLYON
Period21/07/0226/07/02

Cite this

Rinaldi, F., Dowdall, J., Hess, M., Molla, D., & Schwitter, R. (2002). Towards answer extraction: an application to technical domains. In F. Van Harmelen (Ed.), ECAI 2002: 15th European Conference on Artificial Intelligence, proceedings (pp. 460-464). (Frontiers in Artificial Intelligence and Applications; Vol. 77). Amsterdam, Netherlands: IOS Press.