Semantic Dependency Parsing of NomBank and PropBank: An Efficient Integrated Approach via a Large-scale Feature Selection

Abstract

We present an integrated dependencybased semantic role labeling system for English from both NomBank and PropBank. By introducing assistant argument labels and considering much more feature templates, two optimal feature template sets are obtained through an effective feature selection procedure and help construct a high performance single SRL system. From the evaluations on the date set of CoNLL-2008 shared task, the performance of our system is quite close to the state of the art. As to our knowledge, this is the first integrated SRL system that achieves a competitive performance against previous pipeline systems.

Extracted Key Phrases

5 Figures and Tables

Cite this paper

@inproceedings{Zhao2009SemanticDP, title={Semantic Dependency Parsing of NomBank and PropBank: An Efficient Integrated Approach via a Large-scale Feature Selection}, author={Hai Zhao and Wenliang Chen and Chunyu Kit}, booktitle={EMNLP}, year={2009} }