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

^*Corresponding author for this work

Harbin Institute of Technology

Research output: Contribution to conference › Paper › peer-review

44 Citations (Scopus)

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.

Original language	English
Pages	49-54
Number of pages	6
DOIs	https://doi.org/10.3115/1596409.1596417
Publication status	Published - 2009
Externally published	Yes
Event	13th Conference on Computational Natural Language Learning, CoNLL 2009 - Boulder, CO, United States Duration: 4 Jun 2009 → 4 Jun 2009

Conference

Conference	13th Conference on Computational Natural Language Learning, CoNLL 2009
Country/Territory	United States
City	Boulder, CO
Period	4/06/09 → 4/06/09

Access to Document

10.3115/1596409.1596417

Cite this

Che, W., Li, Z., Li, Y., Guo, Y., Qin, B., & Liu, T. (2009). Multilingual dependency-based syntactic and semantic parsing. 49-54. Paper presented at 13th Conference on Computational Natural Language Learning, CoNLL 2009, Boulder, CO, United States. https://doi.org/10.3115/1596409.1596417

@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

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this