Chinese semantic dependency parsing with third-order features

Authors:
Zhijun Wu;Xuan Wang;Xinxin Li
Affiliations:
Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, P. R. China;Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, P. R. China;Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, P. R. China
Venue:
SemEval '12 Proceedings of the First Joint Conference on Lexical and Computational Semantics - Volume 1: Proceedings of the main conference and the shared task, and Volume 2: Proceedings of the Sixth International Workshop on Semantic Evaluation
Year:
2012

Citing 7
Cited 0

Three new probabilistic models for dependency parsing: an exploration

COLING '96 Proceedings of the 16th conference on Computational linguistics - Volume 1
Online large-margin training of dependency parsers

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Discriminative learning and spanning tree algorithms for dependency parsing

Discriminative learning and spanning tree algorithms for dependency parsing
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
The CoNLL-2009 shared task: syntactic and semantic dependencies in multiple languages

CoNLL '09 Proceedings of the Thirteenth Conference on Computational Natural Language Learning: Shared Task
Efficient parsing of syntactic and semantic dependency structures

CoNLL '09 Proceedings of the Thirteenth Conference on Computational Natural Language Learning: Shared Task
Efficient third-order dependency parsers

ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents our system participated on SemEval-2012 task: Chinese Semantic Dependency Parsing. Our system extends the second-order MST model by adding two third-order features. The two third-order features are grand-sibling and tri-sibling. In the decoding phase, we keep the k best results for each span. After using the selected third-order features, our system presently achieves LAS of 61.58% ignoring punctuation tokens which is 0.15% higher than the result of purely second-order model on the test dataset.