A review of methods for word sense disambiguation: machine learning and measures of relatedness and semantic similarity

Abstract

Among the possible solutions for automatic lexical disambiguation in natural language processing tasks, we find methods based on machine learning algorithms, semantic relatedness, and semantic similarity measures. While machine learning methods use endogenous sources of knowledge, semantic relatedness and similarity measures resort to exogenous sources of knowledge, such as definitions from lexicographic resources or lexical meaning relations from ontologies or thesauri, which offer a conceptual hierarchy. In this work, we present and analyze the different types of methods for automatic lexical disambiguation divided into four groups: based on machine learning algorithms, based on semantic relatedness measures, based on semantic similarity measures, and based on hybrid measures. We postulate that the advantage of methods based on relationship and similarity measures lies in the fact that their results are derived from statistical efficiency and linguistic knowledge found in the parameters that make up each of the measures used.