A simple approach to building ensembles of naive Bayesian classifiers for word sense disambiguation

Research output: Contribution to conferencePaperpeer-review

96 Scopus citations

Abstract

This paper presents a corpus-based approach to word sense disambiguation that builds an ensemble of Naive Bayesian classifiers, each of which is based on lexical features that represent co-occurring words in varying sized windows of context. Despite the simplicity of this approach, empirical results disambiguating the widely studied nouns line and interest show that such an ensemble achieves accuracy rivaling the best previously published results.

Original languageEnglish (US)
Pages63-69
Number of pages7
StatePublished - 2000
Event1st Meeting of the North American Chapter of the Association for Computational Linguistics, NAACL 2000 - Seattle, United States
Duration: Apr 29 2000May 4 2000

Conference

Conference1st Meeting of the North American Chapter of the Association for Computational Linguistics, NAACL 2000
Country/TerritoryUnited States
CitySeattle
Period4/29/005/4/00

Bibliographical note

Funding Information:
This work extends ideas that began in collaboration with Rebecca Bruce and Janyce Wiebe. Claudia Leacock and Raymond Mooney provided valuable assistance with the line data. I am indebted to an anonymous reviewer who pointed out the importance of separate test and devtest data sets. A preliminary version of this paper appears in (Pedersen, 2000).

Publisher Copyright:
© ANLP 2000. All rights reserved.

Fingerprint

Dive into the research topics of 'A simple approach to building ensembles of naive Bayesian classifiers for word sense disambiguation'. Together they form a unique fingerprint.

Cite this