Andreas Heß and Nicholas Kushmerick
Emerging Semantic Web standards promise the automated discovery, composition and invocation of Web Services. Unfortunately, this vision requires that services describe themselves with large amounts of hand-crafted semantic metadata. We are investigating the use of machine learning techniques for semi-automatically classifying Web Services and their messages into ontologies. From such semantically-enriched WSDL descriptions, it is straightforward to generate significant parts of a services description in OWL-S or a similar language.