The Impact of Named Entity Normalization on Information Retrieval for Question Answering

TitleThe Impact of Named Entity Normalization on Information Retrieval for Question Answering
Publication TypeConference Paper
Year of Publication2008
Date Published04/2008
AuthorsKhalid MA, Jijkoun VB, de Rijke M
Conference Name30th European Conference on Information Retrieval (ECIR 2008)
Pagination705–710
PublisherSpringer
Abstract

In the named entity normalization task, a system identifies a canonical unambiguous referent for names like "Bush" or "Alabama." Resolving synonymy and ambiguity of such names can benefit end-to-end information access tasks. We evaluate two entity normalization methods based on Wikipedia in the context of both passage and document retrieval for question answering. We find that even a simple normalization method leads to improvements of early precision, both for document and passage retrieval. Moreover, better normalization results in better retrieval performance.

AttachmentSize
ecir2008-nenormalization.pdf119.72 KB