Topic indexing and retrieval for factoid QA

Authors:
Kisuh Ahn;Bonnie Webber
Affiliations:
University of Edinburgh, Edinburgh, UK;University of Edinburgh, Edinburgh, UK
Venue:
IRQA '08 Coling 2008: Proceedings of the 2nd workshop on Information Retrieval for Question Answering
Year:
2008

Citing 7
Cited 1

Learning question classifiers

COLING '02 Proceedings of the 19th international conference on Computational linguistics - Volume 1
Offline strategies for online question answering: answering questions before they are asked

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
REXTOR: a system for generating relations from natural language

RANLPIR '00 Proceedings of the ACL-2000 workshop on Recent advances in natural language processing and information retrieval: held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics - Volume 11
MAYA: a fast Question-answering system based on a predictive answer indexer

ODQA '01 Proceedings of the workshop on Open-domain question answering - Volume 12
Language independent NER using a maximum entropy tagger

CONLL '03 Proceedings of the seventh conference on Natural language learning at HLT-NAACL 2003 - Volume 4
Information extraction for question answering: improving recall through syntactic patterns

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Yago: a core of semantic knowledge

Proceedings of the 16th international conference on World Wide Web

Maintaining passage retrieval information need using analogical reasoning in a question answering task

AIRS'11 Proceedings of the 7th Asia conference on Information Retrieval Technology

Quantified Score

Hi-index	0.00

Visualization

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).