A DLP-Based System for Ontology Representation and Reasoning

Abstract

In the last few years, the need for knowledge-based technologies is emerging in several application areas. Industries are now looking for semantic instruments for knowledge-representation and reasoning. In this context, ontologies (i.e., abstract models of a complex domain) have been recognized to be a fundamental tool; and the World Wide Web Consortium (W3C) has recommended OWL [58] as a standard language for ontologies. Some semantic assumptions of OWL, like Open World Assumption and non- Unique Name Assumption, make sense for the Web, but they are unsuited for Enterprise ontologies, that are specifications of information of business enterprises, which often evolve from relational databases, where both CWA and UNA are adopted. The subject of this thesis is OntoDLV , a system based on Disjunctive Logic Programming (DLP) for the specification and reasoning on enterprise ontologies. OntoDLP, the language of the system, overcomes the above-mentioned limitations of OWL, it adopts both CWA and UNA avoiding ”semantic clash” to enterprise databases. OntoDLP extends DLP with all the main ontology constructs including classes, inheritance, relations and axioms. The language is strongly typed, and includes also complex type constructors, like lists and sets. Importantly, OntoDLV supports a powerful interoperability mechanism with OWL, allowing the user to retrieve information also from OWL Ontologies and to reason on top of that by exploiting OntoDLP powerful deduction rules. The system is endowed with a powerful Application Programming Interface and is already used in a number of real-world applications,including agent-based systems and information extraction applications.