Fast computing grammar-driven convolution tree kernel for semantic role labeling

Wanxiang Che; Min Zhang; Ai Ti Aw; Chew Lim Tan; Ting Liu; Sheng Li

Fast computing grammar-driven convolution tree kernel for semantic role labeling

Wanxiang Che
, Min Zhang
, Ai Ti Aw
, Chew Lim Tan
, Ting Liu
, Sheng Li

School of Computer Science and Technology, Harbin Institute of Technology
Agency for Science, Technology and Research, Singapore
National University of Singapore

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

1 Scopus citations

Abstract

Grammar-driven convolution tree kernel (GTK) has shown promising results for semantic role labeling (SRL). However, the time complexity of computing the GTK is exponential in theory. In order to speed up the computing process, we design two fast grammar-driven convolution tree kernel (FGTK) algorithms, which can compute the GTK in polynomial time. Experimental results on the CoNLL-2005 SRL data show that our two FGTK algorithms are much faster than the GTK.

Original language	English
Pages	781-786
Number of pages	6
State	Published - 2008
Externally published	Yes
Event	3rd International Joint Conference on Natural Language Processing, IJCNLP 2008 - Hyderabad, India Duration: 7 Jan 2008 → 12 Jan 2008

Conference

Conference	3rd International Joint Conference on Natural Language Processing, IJCNLP 2008
Country/Territory	India
City	Hyderabad
Period	7/01/08 → 12/01/08

Cite this

@conference{4140cb44b26c4f3bac93beed14c7bb22,

title = "Fast computing grammar-driven convolution tree kernel for semantic role labeling",

abstract = "Grammar-driven convolution tree kernel (GTK) has shown promising results for semantic role labeling (SRL). However, the time complexity of computing the GTK is exponential in theory. In order to speed up the computing process, we design two fast grammar-driven convolution tree kernel (FGTK) algorithms, which can compute the GTK in polynomial time. Experimental results on the CoNLL-2005 SRL data show that our two FGTK algorithms are much faster than the GTK.",

author = "Wanxiang Che and Min Zhang and Aw, \{Ai Ti\} and Tan, \{Chew Lim\} and Ting Liu and Sheng Li",

note = "Publisher Copyright: {\textcopyright} 2008 IJCNLP 2008 - 3rd International Joint Conference on Natural Language Processing, Proceedings of the Conference. All rights reserved.; 3rd International Joint Conference on Natural Language Processing, IJCNLP 2008 ; Conference date: 07-01-2008 Through 12-01-2008",

year = "2008",

language = "英语",

pages = "781--786",

}

TY - CONF

T1 - Fast computing grammar-driven convolution tree kernel for semantic role labeling

AU - Che, Wanxiang

AU - Zhang, Min

AU - Aw, Ai Ti

AU - Tan, Chew Lim

AU - Liu, Ting

AU - Li, Sheng

PY - 2008

Y1 - 2008

N2 - Grammar-driven convolution tree kernel (GTK) has shown promising results for semantic role labeling (SRL). However, the time complexity of computing the GTK is exponential in theory. In order to speed up the computing process, we design two fast grammar-driven convolution tree kernel (FGTK) algorithms, which can compute the GTK in polynomial time. Experimental results on the CoNLL-2005 SRL data show that our two FGTK algorithms are much faster than the GTK.

AB - Grammar-driven convolution tree kernel (GTK) has shown promising results for semantic role labeling (SRL). However, the time complexity of computing the GTK is exponential in theory. In order to speed up the computing process, we design two fast grammar-driven convolution tree kernel (FGTK) algorithms, which can compute the GTK in polynomial time. Experimental results on the CoNLL-2005 SRL data show that our two FGTK algorithms are much faster than the GTK.

UR - https://www.scopus.com/pages/publications/85120157112

M3 - 论文

AN - SCOPUS:85120157112

SP - 781

EP - 786

T2 - 3rd International Joint Conference on Natural Language Processing, IJCNLP 2008

Y2 - 7 January 2008 through 12 January 2008

ER -

Fast computing grammar-driven convolution tree kernel for semantic role labeling

Abstract

Conference

Other files and links

Fingerprint

Cite this