Semantic Similarity in a Taxonomy by Evaluating the Relatedness of Concept Senses with the Linked Data Semantic Distance

This paper addresses the information-theoretic definition ofsemantic similarity based on the notion of information content, andpresents an evolution of a novel approach for evaluating semantic simi-larity in a taxonomy. Such an approach takes into account not only thegeneric sense of a concept but also its intended sense in a given context.In particular, a method for computing the semantic relatedness of con-cepts in RDF knowledge graphs is used for evaluating the relevance ofthe intended sense of a concept with respect to its generic sense. Theexperiment of this work shows that the relatedness method based ontriple patterns adopted in this paper leads to higher correlation valueswith human judgment with respect to the ones obtained according to theoriginal proposal that is based on a triple weights relatedness measure