Analysis of the methods of word sense disambiguation in the biomedical domain

Abstract

A method for resolving the lexical ambiguity of biomedical terms has been proposed. The method is based on a comparison of «word bags» obtained from the context, definitions and information on related terms from the UMLS metathesaurus [1]. Modification of the method using the analysis of word importance using the statistical measure TF-IDF has been proposed. Experimental verification of the method has been performed on the open test MSH WSD data set [2], developed to support research in the field of lexical resolution.

Keywords

• machine learning
• natural language processing
• word sense disambiguation
• information retrieval