Feature expansion for word sense disambiguation

Nai Lung Tsao, David Wible, Chin Hwa Kuo

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

2 Scopus citations

Abstract

One of the most serious obstacles in research on word sense disambiguation (WSD) is sparseness of training data. This paper describes and motivates a method of feature expansion as a means of resolving the data sparseness problem in supervised corpus-based WSD. The expanded features are extracted from an existing corpus and WordNet automatically. We use our method to supplement the feature expansion approach of [Leacock and Chodorow 1998]. In the experiments, the addition of our method more than doubled the precision improvement over baseline that was obtained by using Leacock and Chodorow's approach alone.

Original languageEnglish
Title of host publicationNLP-KE 2003 - 2003 International Conference on Natural Language Processing and Knowledge Engineering, Proceedings
EditorsChengqing Zong
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages126-131
Number of pages6
ISBN (Electronic)0780379020, 9780780379022
DOIs
StatePublished - 2003
EventInternational Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2003 - Beijing, China
Duration: 26 Oct 200329 Oct 2003

Publication series

NameNLP-KE 2003 - 2003 International Conference on Natural Language Processing and Knowledge Engineering, Proceedings

Conference

ConferenceInternational Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2003
Country/TerritoryChina
CityBeijing
Period26/10/0329/10/03

Keywords

  • Feature expansion
  • Sparseness
  • Word sense disambiguation

Fingerprint

Dive into the research topics of 'Feature expansion for word sense disambiguation'. Together they form a unique fingerprint.

Cite this