Exploring syntactic features for relation extraction using a convolution tree kernel

Min Zhang; Jie Zhang; Jian Su

doi:10.3115/1220835.1220872

Exploring syntactic features for relation extraction using a convolution tree kernel

Min Zhang^*
, Jie Zhang
, Jian Su

^*Corresponding author for this work

Agency for Science, Technology and Research, Singapore

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

89 Scopus citations

Abstract

This paper proposes to use a convolution kernel over parse trees to model syntactic structure information for relation extraction. Our study reveals that the syntactic structure features embedded in a parse tree are very effective for relation extraction and these features can be well captured by the convolution tree kernel. Evaluation on the ACE 2003 corpus shows that the convolution kernel over parse trees can achieve comparable performance with the previous best-reported feature-based methods on the 24 ACE relation subtypes. It also shows that our method significantly outperforms the previous two dependency tree kernels on the 5 ACE relation major types.

Original language	English
Pages	288-295
Number of pages	8
DOIs	https://doi.org/10.3115/1220835.1220872
State	Published - 2006
Externally published	Yes
Event	2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006 - New York, NY, United States Duration: 4 Jun 2006 → 9 Jun 2006

Conference

Conference	2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006
Country/Territory	United States
City	New York, NY
Period	4/06/06 → 9/06/06

Access to Document

10.3115/1220835.1220872

Cite this

@conference{8796e99e4f8e4c679a545b1c65f3e16b,

title = "Exploring syntactic features for relation extraction using a convolution tree kernel",

abstract = "This paper proposes to use a convolution kernel over parse trees to model syntactic structure information for relation extraction. Our study reveals that the syntactic structure features embedded in a parse tree are very effective for relation extraction and these features can be well captured by the convolution tree kernel. Evaluation on the ACE 2003 corpus shows that the convolution kernel over parse trees can achieve comparable performance with the previous best-reported feature-based methods on the 24 ACE relation subtypes. It also shows that our method significantly outperforms the previous two dependency tree kernels on the 5 ACE relation major types.",

author = "Min Zhang and Jie Zhang and Jian Su",

year = "2006",

doi = "10.3115/1220835.1220872",

language = "英语",

pages = "288--295",

note = "2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006 ; Conference date: 04-06-2006 Through 09-06-2006",

}

Zhang, M, Zhang, J & Su, J 2006, 'Exploring syntactic features for relation extraction using a convolution tree kernel', Paper presented at 2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006, New York, NY, United States, 4/06/06 - 9/06/06 pp. 288-295. https://doi.org/10.3115/1220835.1220872

Exploring syntactic features for relation extraction using a convolution tree kernel. / Zhang, Min; Zhang, Jie; Su, Jian.
2006. 288-295 Paper presented at 2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006, New York, NY, United States.

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

TY - CONF

T1 - Exploring syntactic features for relation extraction using a convolution tree kernel

AU - Zhang, Min

AU - Zhang, Jie

AU - Su, Jian

PY - 2006

Y1 - 2006

N2 - This paper proposes to use a convolution kernel over parse trees to model syntactic structure information for relation extraction. Our study reveals that the syntactic structure features embedded in a parse tree are very effective for relation extraction and these features can be well captured by the convolution tree kernel. Evaluation on the ACE 2003 corpus shows that the convolution kernel over parse trees can achieve comparable performance with the previous best-reported feature-based methods on the 24 ACE relation subtypes. It also shows that our method significantly outperforms the previous two dependency tree kernels on the 5 ACE relation major types.

AB - This paper proposes to use a convolution kernel over parse trees to model syntactic structure information for relation extraction. Our study reveals that the syntactic structure features embedded in a parse tree are very effective for relation extraction and these features can be well captured by the convolution tree kernel. Evaluation on the ACE 2003 corpus shows that the convolution kernel over parse trees can achieve comparable performance with the previous best-reported feature-based methods on the 24 ACE relation subtypes. It also shows that our method significantly outperforms the previous two dependency tree kernels on the 5 ACE relation major types.

UR - https://www.scopus.com/pages/publications/84863368822

U2 - 10.3115/1220835.1220872

DO - 10.3115/1220835.1220872

M3 - 论文

AN - SCOPUS:84863368822

SP - 288

EP - 295

T2 - 2006 Human Language Technology Conference - North American Chapter of the Association for Computational Linguistics Annual Meeting, HLT-NAACL 2006

Y2 - 4 June 2006 through 9 June 2006

ER -

Exploring syntactic features for relation extraction using a convolution tree kernel

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this