Please use this identifier to cite or link to this item:
|Title:||Learning predictive structures for Semantic Role Labeling of NomBank|
|Citation:||Liu, C.,Ng, H.T. (2007). Learning predictive structures for Semantic Role Labeling of NomBank. ACL 2007 - Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics : 208-215. ScholarBank@NUS Repository.|
|Abstract:||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 learning algorithm, which extracts the common structures of multiple tasks to improve accuracy, via the use of auxiliary problems. In this paper, we explore a number of different auxiliary problems, and we are able to significantly 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. © 2007 Association for Computational Linguistics.|
|Source Title:||ACL 2007 - Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Dec 29, 2018
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.