Ontology Matching Using an Artificial Neural Network to Learn Weights

Abstract

Ontologies are a formal, declarative knowledge representation model. They form a semantic foundation for many domains, such as Web services, Ecommerce, and the Semantic Web, where applications can mutually understand and share information with each other. However, because ontologies reflect their designers’ conceptual views of part of the world, heterogeneity is an inherent characteristic for ontologies. During (semi)automated matching among ontologies, different semantic aspects, i.e., concept names, concept properties, and concept relationships, contribute in different degrees to the matching result. Therefore, a vector of weights are needed to be assigned to these aspects. It is not trivial to determine what those weights should be, and current research work depends a lot on human heuristics. In this paper, we take an artificial neural network approach to learning and adjusting the above weights, and thereby support a new ontology matching algorithm, with the purpose to avoid some of the disadvantages in both rule-based and learning-based ontology matching approaches.