Skip to main navigation Skip to search Skip to main content

Unsupervised word sense disambiguation using neighborhood knowledge

  • Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Usually ambiguous words contained in article appear several times. Almost all existing methods for unsupervised word sense disambiguation make use of information contained only in ambiguous sentence. This paper presents a novel approach by considering neighborhood knowledge. The approach can naturally make full use of the within-sentence relationship from the ambiguous sentence and cross-sentence relationship from the neighborhood knowledge. Experimental results indicate the proposed method can significantly outperform the baseline method.

Original languageEnglish
Title of host publicationPACLIC 25 - Proceedings of the 25th Pacific Asia Conference on Language, Information and Computation
PublisherInstitute for Digital Enhancement of Cognitive Development, Waseda University.
Pages333-342
Number of pages10
ISBN (Print)9784905166023
Publication statusPublished - 2011
Event25th Pacific Asia Conference on Language, Information and Computation, PACLIC 2011 - Singapore, Singapore
Duration: 16 Dec 201118 Dec 2011

Publication series

NamePACLIC 25 - Proceedings of the 25th Pacific Asia Conference on Language, Information and Computation

Conference

Conference25th Pacific Asia Conference on Language, Information and Computation, PACLIC 2011
Country/TerritorySingapore
CitySingapore
Period16/12/1118/12/11

Keywords

  • Graphbased ranking algorithm
  • Neighborhood knowledge
  • Similarity measure
  • Unsupervised WSD

Fingerprint

Dive into the research topics of 'Unsupervised word sense disambiguation using neighborhood knowledge'. Together they form a unique fingerprint.

Cite this