Raw corpus word sense disambiguation

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

A corpus-based approach is proposed where multiple usages of an ambiguous word are divided into a specified number of sense groups based on features that are automatically obtained from the immediately surrounding raw text. The evaluation of the different methods used for ambiguation is based on the degree to which the discovered sense groups agree with those created by a human judge. Results suggest that some combination of the expectation maximization (EM) algorithm and Gibbs sampling might be beneficial.

Original languageEnglish (US)
Title of host publicationInnovative Applications of Artificial Intelligence - Conference Proceedings
Editors Anon
PublisherAAAI
Number of pages1
StatePublished - Jan 1 1998
EventProceedings of the 1998 10th Conference on Innovative Applications of Artificial Intelligence, IAAI - Madison, WI, USA
Duration: Jul 26 1998Jul 30 1998

Other

OtherProceedings of the 1998 10th Conference on Innovative Applications of Artificial Intelligence, IAAI
CityMadison, WI, USA
Period7/26/987/30/98

Fingerprint Dive into the research topics of 'Raw corpus word sense disambiguation'. Together they form a unique fingerprint.

Cite this