The Web as a Source of Evidence for Filtering Candidate Answers to Natural Language Questions

Author

Bonnefoy, Ludovic ; Bellot, Patrice ; Benoit, Michel

Author_Institution

CERI, Univ. of Avignon, Avignon, France

Volume

1

fYear

2011

Firstpage

63

Lastpage

66

Abstract

Identifying and extracting named entities from web pages has been the subject of many researches. In this paper, we propose and evaluate some new unsupervised language modeling approaches to determine the membership level of a candidate answer, a named entity, to a natural language question to a very fine-grained conceptual class of entity. We propose to address this issue by using the Web or DBPedia hierarchy as sources of evidence. Then, this level of membership can be used to improve the ranking of candidate answers in a question-answering task. Lastly, we present the results we obtained by participating in TREC 2010 Entity track.

Keywords

Internet; information filtering; natural language processing; question answering (information retrieval); DBPedia hierarchy; Web pages; candidate answer filtering; named entity extraction; named entity identification; natural language questions; question-answering task; unsupervised language modeling; Computational modeling; Engines; Ontologies; Organizations; Smoothing methods; Web pages; Web search; Information filtering; Information retrieval; Natural language processing; Question-Answering; TREC Entity;

fLanguage

English

Publisher

ieee

Conference_Titel

Web Intelligence and Intelligent Agent Technology (WI-IAT), 2011 IEEE/WIC/ACM International Conference on

Conference_Location

Lyon

Print_ISBN

978-1-4577-1373-6

Electronic_ISBN

978-0-7695-4513-4

Type

conf

DOI

10.1109/WI-IAT.2011.226

Filename

6040497