Previous abstract | Contents | Next abstract

Semantic Role Labeling Via Generalized Inference Over Classifiers

We present a system submitted to the CoNLL2004 shared task for semantic role labeling. The system is composed of a set of classifiers and an inference procedure used both to clean the classification results and to ensure structural integrity of the final role labeling. Linguistic information is used to generate features during classification and constraints for the inference process.


Vasin Punyakanok, Dan Roth, Wen-tau Yih, Dav Zimak and Yuancheng Tu, Semantic Role Labeling Via Generalized Inference Over Classifiers. In: Proceedings of CoNLL-2004, Boston, MA, USA, 2004, pp. 130-133. [ps] [ps.gz] [pdf] [bibtex]
Last update: May 13, 2003. erikt@uia.ua.ac.be