Query-Oriented Keyphrase Extraction

Publication Type

Conference Proceeding Article

Publication Date

12-2012

Abstract

People often issue informational queries to search engines to find out more about some entities or events. While a Wikipedia-like summary would be an ideal answer to such queries, not all queries have a corresponding Wikipedia entry. In this work we propose to study query-oriented keyphrase extraction, which can be used to assist search results summarization. We propose a general method for keyphrase extraction for our task, where we consider both phraseness and informativeness. We discuss three criteria for phraseness and four ways to compute informativeness scores. Using a large Wikipedia corpus and 40 queries, our empirical evaluation shows that using a named entity-based phraseness criterion and a language model-based informativeness score gives the best performance on our task. This method also outperforms two state-of-the-art baseline methods.

Keywords

Keyphrase extraction, phraseness, informativeness, language model

Discipline

Databases and Information Systems

Publication

Information Retrieval Technology: 8th Asia Information Retrieval Societies Conference (AIRS'12)

Volume

7675

First Page

64

Last Page

75

ISBN

9783642353413

Identifier

10.1007/978-3-642-35341-3_6

Publisher

Springer Verlag

City or Country

Tianjin, China

Additional URL

http://dx.doi.org/10.1007/978-3-642-35341-3_6

This document is currently not available here.

Share

COinS