A MATHEMATICAL MODEL FOR SEMANTIC SIMILARITY MEASURES

Abstract

Semantic similarity between words, concepts or sets of concepts has been a fundamental theme and widely studied in various areas including natural language processing, document semantic comparison, artificial intelligence, semantic web, semantic web service, and semantic search engines. Several similarity measures have been proposed but they are usually tied to special application domains or information representation of various application domains.

In this paper, we present a mathematical model for distance-based semantic similarity estimation in domains that are represented with ontology - an explicit specification of conceptualization of such domains. Based on this model, we construct algorithms to calculate the semantic similarity between two concepts and one between two sets of concepts. The significance of the proposed mathematical model is that it offers a generalization that enables to maintain flexibility and thus supports various computational measures