A new method for semantic similarity assessment using fuzzy formal concept analysis & fuzzy set similarity measure

Abstract

Measuring the accurate semantic similarity between the words is a major issue in various applications of artificial intelligence and computational linguistics areas such as natural language processing, text-mining, information retrieval and for development of semantic web. In the past, many approaches have been proposed and adopted to evaluate similarity by using the knowledge based systems such as WordNet and MeSH ontology. In this paper we have proposed a new method; based on hybridization approach in knowledge based system. In this we have used feature based method and fuzzy Set theory. In feature based approach, properties or features are used for measuring the similarity as compare to edge and content information approaches. Our approach is investigated on standard dataset like R&G, M&C and 353-TC, which shows prominent improvement in the judgment of semantic similarity score between the words. This approach can be further used among cross ontology and fuzzy ontology as it is based on the feature based measure and fuzzy set theory.