Skip to Main Content
Ontology matching is critical to semantic interaction and knowledge sharing. The purpose of ontology matching is to reuse the ontologies and integrate them in different fields. It is the basement of the other semantic Web application, such as, semantic Web-based service, ontology alignment. Nowadays most ontology mapping approaches integrate multiple individual matchers to explore both linguistic and structure similarity of different ontologies. Thus how to effectively aggregating different similarities is pervasive in ontology mapping. However, the achievements of similarities aggregation are very limited. Addressing this issue, the work presented in this paper puts forward an ontology matching approach, which uses as a backbone a multi-similarity matching technique and explores both linguistic and structure similarity. In the process of similarities aggregation, the method based on statistical learning is used. Our approach takes the different similarities into one whole, as a similarity vector. All of them form the similarity space, by this way, matching discovery can be converted into binary classification. SVM (support vector machine) is used to carry on this task. For making full use of the message of ontology, our implementation and experimental results are given to demonstrate the effectiveness of the matching approach.