Multilingual dependency-based syntactic and semantic parsing

Wanxiang Che; Zhenghua Li; Yongqiang Li; Yuhang Guo; Bing Qin; Ting Liu

doi:10.3115/1596409.1596417

Multilingual dependency-based syntactic and semantic parsing

Wanxiang Che^*, Zhenghua Li, Yongqiang Li, Yuhang Guo, Bing Qin, Ting Liu

^*此作品的通讯作者

Harbin Institute of Technology

科研成果: 会议稿件 › 论文 › 同行评审

44 引用（Scopus）

摘要

Our CoNLL 2009 Shared Task system includes three cascaded components: syntactic parsing, predicate classification, and semantic role labeling. A pseudo-projective high-order graph-based model is used in our syntactic dependency parser. A support vector machine (SVM) model is used to classify predicate senses. Semantic role labeling is achieved using maximum entropy (MaxEnt) model based semantic role classification and integer linear programming (ILP) based post inference. Finally, we win the first place in the joint task, including both the closed and open challenges.

源语言	英语
页	49-54
页数	6
DOI	https://doi.org/10.3115/1596409.1596417
出版状态	已出版 - 2009
已对外发布	是
活动	13th Conference on Computational Natural Language Learning, CoNLL 2009 - Boulder, CO, 美国期限: 4 6月 2009 → 4 6月 2009

会议

会议	13th Conference on Computational Natural Language Learning, CoNLL 2009
国家/地区	美国
市	Boulder, CO
时期	4/06/09 → 4/06/09

访问文件

10.3115/1596409.1596417

其它文件与链接

链接到 Scopus 的出版物

引用此

@conference{15c95d924fce4e448a600c91bf9dbc37,

title = "Multilingual dependency-based syntactic and semantic parsing",

abstract = "Our CoNLL 2009 Shared Task system includes three cascaded components: syntactic parsing, predicate classification, and semantic role labeling. A pseudo-projective high-order graph-based model is used in our syntactic dependency parser. A support vector machine (SVM) model is used to classify predicate senses. Semantic role labeling is achieved using maximum entropy (MaxEnt) model based semantic role classification and integer linear programming (ILP) based post inference. Finally, we win the first place in the joint task, including both the closed and open challenges.",

author = "Wanxiang Che and Zhenghua Li and Yongqiang Li and Yuhang Guo and Bing Qin and Ting Liu",

year = "2009",

doi = "10.3115/1596409.1596417",

language = "English",

pages = "49--54",

note = "13th Conference on Computational Natural Language Learning, CoNLL 2009 ; Conference date: 04-06-2009 Through 04-06-2009",

}

TY - CONF

T1 - Multilingual dependency-based syntactic and semantic parsing

AU - Che, Wanxiang

AU - Li, Zhenghua

AU - Li, Yongqiang

AU - Guo, Yuhang

AU - Qin, Bing

AU - Liu, Ting

PY - 2009

Y1 - 2009

N2 - Our CoNLL 2009 Shared Task system includes three cascaded components: syntactic parsing, predicate classification, and semantic role labeling. A pseudo-projective high-order graph-based model is used in our syntactic dependency parser. A support vector machine (SVM) model is used to classify predicate senses. Semantic role labeling is achieved using maximum entropy (MaxEnt) model based semantic role classification and integer linear programming (ILP) based post inference. Finally, we win the first place in the joint task, including both the closed and open challenges.

AB - Our CoNLL 2009 Shared Task system includes three cascaded components: syntactic parsing, predicate classification, and semantic role labeling. A pseudo-projective high-order graph-based model is used in our syntactic dependency parser. A support vector machine (SVM) model is used to classify predicate senses. Semantic role labeling is achieved using maximum entropy (MaxEnt) model based semantic role classification and integer linear programming (ILP) based post inference. Finally, we win the first place in the joint task, including both the closed and open challenges.

UR - http://www.scopus.com/inward/record.url?scp=80053429611&partnerID=8YFLogxK

U2 - 10.3115/1596409.1596417

DO - 10.3115/1596409.1596417

M3 - Paper

AN - SCOPUS:80053429611

SP - 49

EP - 54

T2 - 13th Conference on Computational Natural Language Learning, CoNLL 2009

Y2 - 4 June 2009 through 4 June 2009

ER -

Multilingual dependency-based syntactic and semantic parsing

摘要

会议

访问文件

其它文件与链接

指纹

引用此