Semantic Enrichment in Ontologies for Matching

Abstract

Matching between heterogeneous ontologies becomes crucial for interoperability in distributed and intelligent environments. Although many efforts in ontology mapping have already been conducted, most of them rely heavily on the meaning of entity names, rather than the semantics defined in ontologies. In order to deal with semantic heterogeneity, we propose a semantically enriched model of ontologies (called MetaOntoModel) where every domain concept is treated as a sort—an entity type that carries identity criteria for its instances—and classified these concepts based on three philosophical notions: identity, rigidity, and dependency. According to the classification, concept-level properties (called meta-knowledge) are embedded for each concept. Our novel idea is that if two concepts are semantically equivalent, then they have the same meta-knowledge. On the contrary, if two concepts possess different kinds of meta knowledge, then they cannot be matched. We also prove that meta-knowledge can determine not only the scope of semantic correspondences, but also which properties are the most relevant in finding correspondence between two similar concepts.