A Method for Word Sense Disambiguation of Unrestricted Text

Description:

This paper discusses a method for word sense disambiguation of unrestricted text.

Creator(s):
Creation Date: June 1999
Partner(s):
UNT College of Engineering
Collection(s):
UNT Scholarly Works
Usage:
Total Uses: 65
Past 30 days: 15
Yesterday: 0
Creator (Author):
Mihalcea, Rada, 1974-

University of North Texas; Southern Methodist University

Creator (Author):
Moldovan, Dan I.

Southern Methodist University

Date(s):
  • Creation: June 1999
Description:

This paper discusses a method for word sense disambiguation of unrestricted text.

Degree:
Note:

Abstract: Selecting the most appropriate sense for an ambiguous word in a sentence is a central problem in Natural Language Processing. In this paper, the authors present a method that attempts to disambiguate all the nouns, verbs, adverbs and adjectives in a text, using the senses provided in WordNet. The senses are ranked using two sources of information: (1) the Internet for gathering statistics for word-word co-occurrences and (2) WordNet for measuring the semantic density for a pair of words. The authors report an average accuracy of 80% for the first ranked sense, and 91% for the first two ranked senses. Extensions of this method for larger windows of more than two words are considered.

Physical Description:

7 p.

Language(s):
Subject(s):
Keyword(s): natural language processing | word sense disambiguation | WordNet
Source: Thirty-Seventh Annual Meeting of the Association for Computational Linguistics (ACL), 1999, College Park, Maryland, United States
Contributor(s):
Partner:
UNT College of Engineering
Collection:
UNT Scholarly Works
Identifier:
  • ARK: ark:/67531/metadc83302
Resource Type: Paper
Format: Text
Rights:
Access: Public