Adaptive Word Sense Disambiguation Using Lexical Knowledge in a Machine-readable Dictionary

Abstract

This paper describes a general framework for adaptive conceptual word sense disambiguation. The proposed system begins with knowledge acquisition from machine-readable dictionaries. Central to the approach is the adaptive step that enriches the initial knowledge base with knowledge gleaned from the partial disambiguated text. Once the knowledge base is adjusted to suit the text at hand, it is applied to the text again to finalize the disambiguation decision. Definitions and example sentences from the Longman Dictionary of Contemporary English are employed as training materials for word sense disambiguation, while passages from the Brown corpus and Wall Street Journal (WSJ) articles are used for testing. An experiment showed that adaptation did significantly improve the success rate. For thirteen highly ambiguous words, the proposed method disambiguated with an average precision rate of 70.5% for the Brown corpus and 77.3% for the WSJ articles.