Sparse bayesian classification of predicate arguments

Summary, in English

We present an application of Sparse Bayesian Learning to the task of semantic role labeling, and we demonstrate that this method produces smaller classifiers than the popular Support Vector approach. We describe the classification strategy and the features used by the classifier. In particular, the contribution of six parse tree path features is investigated.

• Författare: Richard Johansson; Pierre Nugues
• Avdelning/ar: Institutionen för datavetenskap; Robotik och Semantiska System
• Publiceringsår: 2005
• Språk: Engelska
• Sidor: 177-200
• Publikation/Tidskrift/Serie: CoNLL-2005: Proceedings of the Ninth Conference on Computational Natural Language Learning, 43rd Annual Meeting of the Association of Computational Linguistics
• Länkar: http://www.aclweb.org/anthology/W05-0624.pdf
• Dokumenttyp: Konferensbidrag
• Förlag: Association for Computational Linguistics
• Ämne: Computer Science
• Nyckelord: machine learning; Natural language processing; semantic analysis
• Conference name: Ninth Conference on Computational Natural Language Learning
• Conference date: 2005-06-29 - 2005-06-30
• Conference place: Ann Arbor, United States
• Status: Published