Basser Seminar Series

Enriching and using large-scale lexico-semantic resources

Dr Eneko Agirre
University of the Basque Country

Friday August 3, 2007, 10-11 am **Note different day and time

School of IT Building, Laboratory 1W-114, Level 1 ** Note different location


This talk presents a research line for the semantic processing of natural language. Current limitations of semantic interpretation systems stem from the pervasive ambiguity in natural language. Our working hypothesis is that a complex mixture of resources (ranging from hand-made knowledge bases, lexicons and hand-tagged corpora to raw corpora) and machine learning strategies built by different researchers need to be integrated in order to advance the state-of-the-art. An architecture using the EuroWordNet design will be presented, with some examples of integrating both hand-made resources and automatically learned relations. Finally, some promising applications on CLIR are presented, as well as the ongoing SemEval 07 / CLEF
2008 exercise on evaluating the contribution of WSD to CLIR.

Speaker's biography

Dr. Agirre received his PhD (1999) and B.A. (1990) in Computer Science by the University of the Basque Country, M.Sc. (1991) in Cognitive Science by the University of Edinburgh. He is currently an associate professor in the Computer Science Faculty of the University of the Basque Country since 1995. He has published over 90 refereed articles and conference papers in Natural Language Processing, mainly in the areas of Lexical Knowledge Acquisition and Word Sense Disambiguation. He is co-editor of the Springer book "Word Sense Disambiguation". He is a usual program committee member of several conferences, including the Empirical Methods in Natural Language Processing conference, the Computational Natural Language Learning conference, the Text Speech and Dialogue Conference, the Global WordNet Conferences and several workshops in major conferences (ECAI, ACL and COLING). He is a usual reviewer for several major conferences including IJCAI, ACL, HLT, COLING and EMNLP, and several journals including LRE (formerly CHUM), NLE and JSL. He has been the site coordinator and workpackage leader of major projects, including the HERMES Spanish national project and the MEANING European Commission 5FP project. He is organizing the SemEval-2007 semantic evaluation competition and workshop.