File(s) under permanent embargo
Can shallow semantic class information help answer passage retrieval?
conference contribution
posted on 2009-01-01, 00:00 authored by Bahadorreza OfoghiBahadorreza Ofoghi, John YearwoodJohn YearwoodIn this paper, the effect of using semantic class overlap evidence in enhancing the passage retrieval effectiveness of question answering (QA) systems is tested. The semantic class overlap between questions and passages is measured by evoking FrameNet semantic frames using a shallow term-lookup procedure. We use the semantic class overlap evidence in two ways: i) fusing passage scores obtained from a baseline retrieval system with those obtained from the analysis of semantic class overlap (fusion-based approach), and ii) revising the passage scoring function of the baseline system by incorporating semantic class overlap evidence (revision-based approach). Our experiments with the TREC 2004 and 2006 datasets show that the revision-based approach significantly improves the passage retrieval effectiveness of the baseline system.
History
Event
Australasian Artificial Intelligence. Joint Conference (22nd : 2009 : Melbourne, Vic.)Volume
5866Series
Lecture notes in computer sciencePagination
587 - 596Publisher
Springer-VerlagLocation
Melbourne, VictoriaPlace of publication
Berlin, GermanyPublisher DOI
Start date
2009-12-01End date
2009-12-04ISSN
0302-9743eISSN
1611-3349ISBN-13
9783642104381ISBN-10
364210438XLanguage
engPublication classification
E1.1 Full written paper - refereed; E Conference publicationCopyright notice
2009, Springer-Verlag Berlin HeidelbergEditor/Contributor(s)
A Nicholson, X LiTitle of proceedings
AI 2009 : Advances in Artificial Intelligence : Proceedings of the 22nd Australasian Joint ConferenceUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC