Refining ontologies via pattern-based clustering

In this paper we consider the problem of finding subconcepts of a known concept (reference concept) in a given ontology in the light of new knowledge coming from a data source. These subconcepts are discovered by looking for frequent association patterns between the reference concept and other concepts also occurring in the existing ontology. As an illustration, we report preliminary results obtained from the refinement of an ALC ontology with respect to DATALOG data extracted from the on-line CIA World Fact Book.