V. Claveau > Publications > GL2001 Abstract OLST Version française Pierrette Bouillon and Vincent Claveau and Cécile Fabre and Pascale Sébillot Using Part-of-Speech and Semantic Tagging for the Corpus-Based Learning of Qualia Structure Elements, First international workshop on Generative Approaches to the Lexicon (GL'2001), Geneva, Switzerland, April 2001, Document (ps) Abstract This paper describes the implementation and results of a machine learning method, developed within the inductive logic programming (ILP) framework [Muggleton 94], to automatically extract, from a corpus tagged with parts of speech (POS) and semantic classes, noun-verb pairs whose components are bound by one of the relations defined in the qualia structure in the Generative Lexicon [Pustejovsky 95]. We demonstrate that the semantic tagging of the corpus improves the quality of the learning, both on a theoretical and an empirical point of view. We also show that a set of the rules learnt by our ILP method have a linguistic significance regarding the detection of the clues that distinguish, in terms of POS and semantic surrounding context, noun-verb pairs that are linked by one qualia role from others that are not semantically related.