A Method of Ontology Mapping Based on Subtree Kernel

In semantic web, ontology mapping is the basis of the interoperation of heterogeneous ontologies. Ontologies are usually distributed and heterogeneous and thus it is necessary to find the mapping between them before processing across them. The current ontology mapping methods mainly make the contribution of adjacent nodes into consideration but merely use the characteristic of substructure. This paper proposes a method of ontology mapping based on subtree kernel which uses the influence of substructure to node´s similarity and adjusts the similarity with hyponymy or hypernymy relation of WordNet; We evaluate our approach with experiments which demonstrate that our solution yields a higher accuracy and recall.