Towards linked open data enabled ontology learning from text

Abstract

The artifacts produced by current (semi-)automatic methods of ontology learning from text have yet to be improved so that they can provide significant support in creating rich and expressive ontologies. Hence, it is our goal in this study to explore ways to create much more enriched ontologies. In this short paper, we discuss the hypotheses of a PhD work, which addresses the problem of how to reuse the freely available knowledge in Linked Open Data as background knowledge beside text in order to extract new ontological or assertional knowledge for creating a more enriched ontology. In other words, we hypothesize that by using the extra knowledge in large RDF datasets in Linked Open Data cloud, the functions associated with the layers of Ontology Learning Stack could be improved, resulting in more enriched ontologies.