Loading...
Thumbnail Image
Item

Multi-argument classification for semantic role labeling

Abstract
This paper describes a Multi-Argument Classification (MAC) approach to Semantic Role Labeling. The goal is to exploit dependencies between semantic roles by simultaneously classifying all arguments as a pattern. Argument identification, as a pre-processing stage, is carried at using the improved Predicate-Argument Recognition Algorithm (PARA) developed by Lin and Smith (2006). Results using standard evaluation metrics show that multi-argument classification, archieving 76.60 in F₁ measurement on WSJ 23, outperforms existing systems that use a single parse tree for the CoNLL 2005 shared task data. This paper also describes ways to significantly increase the speed of multi-argument classification, making it suitable for real-time language processing tasks that require semantic role labelling.
Type
Conference Contribution
Type of thesis
Series
Citation
Lin, C.-S. A., & Smith, T. C. (2008). Multi-Argument classification for semantic role labeling. In Proceedings of the First International Workshop on Automated Syntactic Annotations for Interoperable Language Resources, Hong Kong, 8 January 2008 (pp. 53-60).
Date
2008
Publisher
City University of Hong Kong
Degree
Supervisors
Rights