Building Rules on Top of Ontologies for the Semantic Web with Inductive Logic Programming

Abstract

Building rules on top of ontologies is the ultimate goal of the logical layer of the Semantic Web. To this aim an ad-hoc mark-up language for this layer is currently under discussion. It is intended to follow the tradition of hybrid knowledge representation and reasoning systems such as AL-log that integrates the description logic ALC and the function-free Horn clausal language Datalog. In this paper we consider the problem of automating the acquisition of these rules for the Semantic Web. We propose a general framework for rule induction that adopts the methodological apparatus of Inductive Logic Programming and relies on the expressive and deductive power of AL-log. The framework is valid whatever the scope of induction (description vs. prediction) is. Yet, for illustrative purposes, we also discuss an instantiation of the framework which aims at description and turns out to be useful in Ontology Refinement.

Class expression learning for ontology engineering

“…Other approaches, e.g. [26] focus on learning in hybrid knowledge bases combining ontologies and rules. Ontology evolution [27] has been discussed in this context.…”

DC Proposal: Ontology Learning from Noisy Linked Data

“…et al have done a series of work on learning rules. In [15] hypotheses are represented as AL-log rules, and the coverage relations are defined on the basis of query answering in AL-log. Correspondingly, [16] learns DL-log rules, besides the differences in the expressive power of the target language, it also reformulate the coverage relation and the generality relation as satisfiability problems.…”

ORE - A Tool for Repairing and Enriching Knowledge Bases

“…DL-FOIL [5] is a similar approach mixing upward and downward refinement. Other approaches focus on learning in hybrid language settings [26].…”