Lexical disambiguation: sources of information and their statistical realization

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

Abstract

Lexical disambiguation can be achieved using different sources of information. Aiming at high performance of automatic disambiguation it is important to know the relative importance and applicability of the various sources. In this paper we classify several sources of information and show how some of them can be achieved using statistical data. First evaluations indicate the extreme importance of local information, which mainly represents lexical associations and selectional restrictions for syntactically related words.
Original languageAmerican English
Title of host publication29th annual meeting on Association for Computational Linguistics
PublisherAssociation for Computational Linguistics
StatePublished - 1991

Bibliographical note

Place of conference:Berkeley, California

Fingerprint

Dive into the research topics of 'Lexical disambiguation: sources of information and their statistical realization'. Together they form a unique fingerprint.

Cite this