Language technologies meet ontology acquisition

Abstract

This paper overviews and analyses the on-going research attempts to apply language technologies to automatic ontology acquisition. At first glance there are many successful approaches in this very hot field. However, most of them aim at the extraction of named entities as well as draft taxonomies and partonomies. Only few attempts exist for enriching ontologies by applying word-sense disambiguation. There are principle obstacles to extract automatically coherent conceptualisations from raw texts: it is impossible to identify exactly the types and their instances as well as the word meanings which denote types. It is also impossible to validate a text-based conceptual model against the real world. Thus we can expect only partial success in the semi-automatic acquisition in specific (limited) domains, by workbenches supporting the human knowledge engineer in the final ontological choices. © Springer-Verlag Berlin Heidelberg 2005.