Softer concepts mean smarter queries

The vision of a semantic Web incorporates many aspects which require flexible knowledge representation, learning and reasoning. These include: the mismatch between crisp hierarchical structures and the \´fuzzier" real world in which objects may have partial membership in classes; notions of approximate equality in data, and semantic equivalence of syntactically different structures; and robustness against inconsistent, missing, partial or incorrect data. In this paper we outline a system which uses concept hierarchies to focus queries. We concentrate on the need to avoid rigid definitions and allow uncertainty in the concept hierarchy, in order to combine diverse data sources.