The Datalog Combination of Deduction

Permission is granted to quote short excerpts and to reproduce figures and tables from this report, provided that the source of such material is fully acknowledged. Uniting ontologies and rules has become a central topic in the Semantic Web. Bridging the discrepancy between these two knowledge representations, this paper introduces Datalog DL as a family of hybrid languages, where Datalog rules are parameterized by various DL (description logic) languages ranging from ALC to SHIQ. Making Datalog DL a decidable system with complexity of EXPTIME, we propose independent properties in the DL body as the restriction to hybrid rules, and weaken the safeness condition to balance the trade-off between expressivity and reasoning power. Building on existing well-developed techniques, we present a principled approach to enrich (RuleML) rules with information from (OWL) ontologies, and develop a prototype system combining a rule engine (OO jDREW) with a DL reasoner (RACER).