Dependency tree-based SRL with proper pruning and extensive feature engineering

Authors:
Hongling Wang;Honglin Wang;Guodong Zhou;Qiaoming Zhu
Affiliations:
Soochow University, Suzhou, China;Soochow University, Suzhou, China;Soochow University, Suzhou, China;Soochow University, Suzhou, China
Venue:
CoNLL '08 Proceedings of the Twelfth Conference on Computational Natural Language Learning
Year:
2008

Citing 8
Cited 0

Automatic labeling of semantic roles

Computational Linguistics
The necessity of parsing for predicate argument recognition

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Pseudo-projective dependency parsing

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Semantic role labeling using different syntactic views

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Semantic role labeling using dependency trees

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Non-projective dependency parsing using spanning tree algorithms

HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
The CoNLL-2008 shared task on joint parsing of syntactic and semantic dependencies

CoNLL '08 Proceedings of the Twelfth Conference on Computational Natural Language Learning
Generalized inference with multiple semantic role labeling systems

CONLL '05 Proceedings of the Ninth Conference on Computational Natural Language Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a dependency tree-based SRL system with proper pruning and extensive feature engineering. Official evaluation on the CoNLL 2008 shared task shows that our system achieves 76.19 in labeled macro F1 for the overall task, 84.56 in labeled attachment score for syntactic dependencies, and 67.12 in labeled F1 for semantic dependencies on combined test set, using the standalone MaltParser. Besides, this paper also presents our unofficial system by 1) applying a new effective pruning algorithm; 2) including additional features; and 3) adopting a better dependency parser, MSTParser. Unofficial evaluation on the shared task shows that our system achieves 82.53 in labeled macro F1, 86.39 in labeled attachment score, and 78.64 in labeled F1, using MSTParser on combined test set. This suggests that proper pruning and extensive feature engineering contributes much in dependency tree-based SRL.