This paper introduces a method and a tool for automatically aligning OWL ontologies, a crucial step for achieving the interoperability of heterogeneous systems in the Semantic Web. Different components are combined for finding suitable mapping candidates (together with their weights), and the set of rules with maximum matching probability is selected. Machine learning-based classifiers and a new classifier using the structure and the semantics of the OWL ontologies are proposed. Our method has been implemented and evaluated on an independent test set provided by an international ontology alignment contest. We provide the results of this evaluation with respect to the other competitors.

Additional Metadata
THEME Information (theme 2)
Conference International Conference on Web Information Systems Engineering
Citation
Straccia, U, & Troncy, R. (2005). oMAP: Combining Classifiers for Aligning OWL Ontologies. In Proceedings of International Conference on Web Information Systems Engineering 2005 (6) (pp. 133–147).