Evaluation of linguistic similarity measurement techniques for ontology alignment

Abstract

To bridge the semantic gap between different offered ontologies, Ontology Engineers have proposed and implemented various matching techniques during the last decade. Still, these techniques require more efforts and investigations to achieve better precision and recall for the set of alignments. The ontology alignment process consists of mainly three different stages; namely, String based, Linguistic based and Structure based. This paper presents the evaluation and analysis of various linguistic based ontology alignment techniques and their performance during the overall alignment process. For this purpose, we have included those linguistic matching tools which are widely used in the alignment systems whose performance is relatively better in terms of precision and recall during the tests conducted for Ontology Alignment Evaluation Initiative (OAEI). The results presented in this paper were obtained using benchmark ontologies used in OAEI conference. The results and analysis shows the significance of linguistic tools in the overall alignment process. The analysis presented in this paper can also be used as future guidelines for the research community who utilizes the linguistic matchers for finding the semantically equal entities from different ontologies.