Topic Indexing and Retrieval for Factoid QA

Kisuh Ahn, Bonnie Webber

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

Abstract

The method of Topic Indexing and Retrieval for QA persented in this paper enables fast and efficent QA for questions with named entity answers. This is achieved by identifying all possible named entity answers in a corpus off-line and gathering all possible evidence for their direct retrieval as answer candidates using standard IR techniques. An evaluation of this method on 377 TREC questions produced a score of 0.342 in Accuracy and 0.413 in Mean Reciprocal Rank (MRR).
Original languageEnglish
Title of host publicationColing 2008: Proceedings of the 2Nd Workshop on Information Retrieval for Question Answering
Place of PublicationStroudsburg, PA, USA
PublisherAssociation for Computational Linguistics
Pages66-73
Number of pages8
ISBN (Print)978-1-905593-55-2
Publication statusPublished - 2008

Publication series

NameIRQA '08
PublisherAssociation for Computational Linguistics

Cite this