Paper: Learning Predictive Structures for Semantic Role Labeling of NomBank

ACL ID P07-1027
Title Learning Predictive Structures for Semantic Role Labeling of NomBank
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2007
Authors

This paper presents a novel application of Alternating Structure Optimization (ASO) to the task of Semantic Role Labeling (SRL) of noun predicates in NomBank. ASO is a recently proposed linear multi-task learn- ing algorithm, which extracts the common structures of multiple tasks to improve accu- racy, via the use of auxiliary problems. In this paper, we explore a number of different auxiliary problems, and we are able to sig- nificantly improve the accuracy of the Nom- Bank SRL task using this approach. To our knowledge, our proposed approach achieves the highest accuracy published to date on the English NomBank SRL task.