IROM: Information Retrieval-Based Ontology Matching
Résumé
Abstract. A crucial piece of semantic web development is the creation of viable ontology matching approaches to ensure interoperability in a wide range of applications such as information integration and semantic multimedia. In this paper, a new approach for ontology matching called IROM (Information Retrieval-based Ontology Matching) is presented. This approach derives the different components of an information retrieval (IR) framework based on the information provided by the input ontologies and supported by ontology similarity measures. Subsequently, a retrieval algorithmis applied to determine the correspondences between the matched ontologies. IROMwas tested with ontology pairs taken from two resources for reference ontologies, OAEI and FOAM. The evaluation shows that IROM is competitive with top-ranked matchers on the bench- mark test at OAEI campaign of 2009.