Research Center for Information Retrieval, School of Computer Science and Technology, Harbin Institute of Technology, Harbin, Heilongjiang 150001, China
We propose a high-order parsing model which uses all grandchildren nodes to compose high-order features, constrains the searching space by the beam-search strategy, and finds the approximately optimal dependency tree. In addition, we explore rich dependency label features and allow multiple relations for one arc during decoding. In the CoNLL 2009 international evaluation task of multilingual syntactic and semantic dependency parsing, this method ranks first in the joint task, and third in the syntactic parsing task. Key wordscomputer application; Chinese information processing; Beam-search; High-order Model; Dependency Parsing
LI Zhenghua, CHE Wanxiang, LIU Ting.
Beam-Search Based High-Order Dependency Parser. Journal of Chinese Information Processing. 2010, 24(1): 37-42
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Michael A. Covington. A fundamental algorithm for dependency parsing [C]//Proceedings of the 39th Annual ACM Southeast Conference,2001. [2] Hiroyasu Yamada, Yuji Matsumoto. Statistical dependency analysis with support vector machines [C]// Proceedings of 8th International Workshop on Parsing Technologies. 2003:195-206. [3] Joakim Nivre, Mario Scholz. Deterministic Dependency Parsing of English Text [C]//Proceedings of COLING. 2004:64-70. [4] Jason Eisner. Bilexical grammars and a cubic-time probabilistic parser [C]//Proceedings of the International Workshop on Parsing Technologies, MIT. 1997: 54-65. [5] Ryan McDonald, Koby Crammer and Fernando Pereira. Online Large-Margin Training of Dependency Parsers [C]//Association for Computational Linguistics (ACL). 2005. [6] Ryan McDonald and Fernando Pereira. Online Learning of Approximate Dependency Parsing Algorithms [C]//European Association for Computational Linguistics (EACL). 2006. [7] Xavier Carreras. Experiments with a high-order projective dependency parser [C]//Proceedings of the CoNLL 2007 Shared Task Session of EMNLP-CoNLL. 2007:957-961. [8] Joakim Nivre and J. Nilsson. Pseudo-Projective Dependency Parsing [C]//Proc. of the 43rd Annual Meeting of the ACL. 2005: 99-106. [9] Wanxiang Che, Zhenghua Li, Yuxuan Hu, Yongqiang Li, Bing Qin, Ting Liu, Sheng Li. A Cascaded Syntactic and Semantic Dependency Parsing System [C]//CoNLL 2008: Proceedings of the 12th Conference on Computational Natural Language Learning, 2008: 238-242.
PDF(539 KB)
