Semantic Role Labeling Using a Grammar-Driven Convolution Tree Kernel

Convolution tree kernel has shown promising results in semantic role labeling (SRL). However, this kernel does not consider much linguistic knowledge in kernel design and only performs hard matching between subtrees. To overcome these constraints, this paper proposes a grammar-driven convolution tre...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on audio, speech, and language processing speech, and language processing, 2008-09, Vol.16 (7), p.1315-1329
Main Authors: Zhang, Min, Che, Wanxiang, Zhou, Guo Dong, Aw, Aiti, Tan, Chew Lim, Liu, Ting, Li, Sheng
Format: Article
Language:English
Subjects:
Approximation
Computer science
Convolution
Councils
Data mining
Dynamic programming
grammar-driven convolution tree kernel
Kernel
Kernels
Labeling
Linguistics
Matching
Natural language processing
Natural languages
Polynomials
Research and development
semantic role labeling
Semantics
Studies
Trees
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Convolution tree kernel has shown promising results in semantic role labeling (SRL). However, this kernel does not consider much linguistic knowledge in kernel design and only performs hard matching between subtrees. To overcome these constraints, this paper proposes a grammar-driven convolution tree kernel for SRL by introducing more linguistic knowledge. Compared with the standard convolution tree kernel, the proposed grammar-driven kernel has two advantages: 1) grammar-driven approximate substructure matching, and 2) grammar-driven approximate tree node matching. The two approximate matching mechanisms enable the proposed kernel to better explore linguistically motivated structured knowledge. Experiments on the CoNLL-2005 SRL shared task and the PropBank I corpus show that the proposed kernel outperforms the standard convolution tree kernel significantly. Moreover, we present a composite kernel to integrate a feature-based polynomial kernel and the proposed grammar-driven convolution tree kernel for SRL. Experimental results show that our composite kernel-based method significantly outperforms the previously best-reported ones.
ISSN:1558-7916
2329-9290
1558-7924
2329-9304
DOI:10.1109/TASL.2008.2001104