Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

The Role of Semantic Roles in Disambiguating Verb Senses

Published

Author(s)

Hoa T. Dang, Martha S. Palmer

Abstract

We describe an automatic Word Sense Disambiguation (WSD) system that disambiguates verb senses using syntactic and semantic features that encode information about predicate arguments and semantic classes. Our system performs better than the best published results on the English verbs of senseval-2. We also experiment with using the gold-standard predicate-argument labels from PropBank to disambiguate fine-grained WordNet senses and course-grained PropBank framesets, and show that WSD can be further improved with better extraction of semantic roles.
Proceedings Title
Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics
Conference Dates
June 25-30, 2005
Conference Location
Ann Arbor, MI
Conference Title
Association for Computational Linguistics

Keywords

maximum entropy models, predicate-arguments, verb sense disambiguation

Citation

Dang, H. and Palmer, M. (2005), The Role of Semantic Roles in Disambiguating Verb Senses, Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics, Ann Arbor, MI, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=150245 (Accessed June 16, 2024)

Issues

If you have any questions about this publication or are having problems accessing it, please contact reflib@nist.gov.

Created December 19, 2005, Updated February 19, 2017