Passage retrieval for question answering using sliding windows

Open Access
Authors
Publication date 2008
Book title Coling 2008: 22nd International Conference on Computational Linguistics: Proceedings of the 2nd workshop on Information Retrieval for Question Answering
ISBN
  • 9781905593552
Event 2nd workshop on Information Retrieval for Question Answering (IR4QA), Manchester, UK
Pages (from-to) 26-33
Publisher Stroudsburg, PA: Association for Computational Linguistics (ACL)
Organisations
  • Faculty of Science (FNWI) - Informatics Institute (IVI)
Abstract
The information retrieval (IR) community has investigated many different techniques to retrieve passages from large collections of documents for question answering (QA). In this paper, we specifically examine and quantitatively compare the impact of passage retrieval for QA using sliding windows and disjoint windows. We consider two different data sets, the TREC 2002-2003 QA data set, and 93 whyquestions against INEX Wikipedia. We discovered that, compared to disjoint windows, using sliding windows results in improved performance of TREC-QA in terms of TDRR, and in improved performance of why-QA in terms of success@n and MRR.
Document type Conference contribution
Note Copyright information: http://creativecommons.org/licenses/by-nc-sa/3.0/
Language English
Published at http://aclweb.org/anthology-new/W/W08/W08-1804.pdf
Downloads
296637.pdf (Final published version)
Permalink to this page
Back