Indian Journal of Science and Technology

Abstract

The technique of ontology matching acts as a prerequisite for performing various activities in the semantic web. Most Ontology matching methods compare class names only based on their similarity irrespective of their real meaning; failed to specify the type of semantic relation. The proposed hybrid layered approach calculates syntactic, semantic and structural similarity between the classes from input ontologies in successive layers. Finally, the alignment layer generates the final matching results by combining the results obtained from the previous layers and generates semantic mappings between them. This approach overcomes the risk of generating incorrect matching results. The test dataset from OAEI are used for evaluating the proposed hybrid approach. The results obtained proved that the proposed approach overtakes the other existing methods by generating correct matching results thereby improving the accuracy of the results achieved. This approach can also be applied to match other entities of the ontology. Since the layers provide matching results based on user – defined threshold, it has the advantage of excluding the incorrect mappings. Thus the proposed hybrid layered approach helps to learn the knowledge hidden between the local ontologies leading to the improved precision.
Keywords: Linguistic Features, Ontology Classes, Ontology Matching, Semantic Relations, Synset