Please use this identifier to cite or link to this item:
Title: Semantic role labeling using a grammar-driven convolution tree kernel
Authors: Zhang, M.
Che, W.
Zhou, G.
Aw, A.
Tan, C.L. 
Liu, T.
Li, S.
Keywords: Dynamic programming
Grammar-driven convolution tree kernel
Natural languages
Semantic role labeling
Issue Date: 2008
Citation: Zhang, M., Che, W., Zhou, G., Aw, A., Tan, C.L., Liu, T., Li, S. (2008). Semantic role labeling using a grammar-driven convolution tree kernel. IEEE Transactions on Audio, Speech and Language Processing 16 (7) : 1315-1329. ScholarBank@NUS Repository.
Abstract: 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. © 2008 IEEE.
Source Title: IEEE Transactions on Audio, Speech and Language Processing
ISSN: 15587916
DOI: 10.1109/TASL.2008.2001104
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Mar 21, 2019


checked on Mar 11, 2019

Page view(s)

checked on Mar 24, 2019

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.