Eniafe Festus Ayetiran, Guido Boella, Luigi Di Caro, and Livio Robaldo

Enhancing Word Sense Disambiguation Using A Hybrid Knowledge-Based Technique

Abstract: In this paper, we present a method for enhancing Word Sense Disambiguation through a hybrid system derived from the combination of Jiang & Conrath’s similarity measure and a modified version of the original Lesk’s algorithm by validating their results. The validation was carried out by computing the cumulative maximum overlap scores between the glosses of the senses returned by each of the algorithms and that of their semantically related senses in the WordNet lexical taxonomy with the original sentence containing the target word being disambiguated. Evaluation performed using the coarse-grained ...

Get Natural Language Processing and Cognitive Science now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.