Verifying DAML+OIL and beyond in Z/EVES

Abstract

Semantic Web, the next generation of Web, gives data well-defined and machine-understandable meaning so that they can be processed by remote intelligent agents cooperatively. Ontology languages are the building blocks of Semantic Web as they prescribe how data are defined and related. The existing reasoning and verification tools for Semantic Web are improving however still elementary. We believe that Semantic Web can be a novel application domain for software modeling languages and tools. Z is a formal modeling language for specifying software systems and Z/EVES is a proof tool for Z. In this paper, we firstly present Z semantics for ontology language DAML+OIL. This semantic model is embedded as a Z section daml2z in Z/EVES, which serves as an environment for checking and verifying Web ontologies. Then we present a tool for automatically transforming ontology documents into the specialized Z codes understood by Z/EVES. Finally, we use a recent real application, the military plan ontologies, to demonstrate the different reasoning tasks that Z/EVES can perform. Furthermore, undiscovered errors in the original ontologies were found by Z/ EVES and some of these errors are even beyond Semantic Web modeling and reasoning capabilities.