Portal de Periódicos da CAPES

OMEN: A Probabilistic Ontology Mapping Tool

2005; Springer Science+Business Media; Linguagem: Inglês

10.1007/11574620_39

1611-3349

Prasenjit Mitra, Natasha Noy, Anuj Jaiswal,

Service-Oriented Architecture and Web Services

Most existing ontology mapping tools are inexact. Inexact ontology mapping rules, if not rectified, result in imprecision in the applications that use them. We describe a framework to probabilistically improve existing ontology mappings using a Bayesian Network. Omen, an Ontology Mapping ENhancer, is based on a set of meta-rules that captures the influence of the ontology structure and the existing matches to match nodes that are neighbours to matched nodes in the two ontologies. We have implemented a protype ontology matcher that can either map concepts across two input ontologies or enhance existing matches between ontology concepts. Preliminary experiments demonstrate that Omen enhances existing ontology mappings in our test cases.