A Hybrid Convolution Tree Kernel for Semantic Role Labeling

A hybrid convolution tree kernel is proposed in this paper to effectively model syntactic structures for semantic role labeling (SRL). The hybrid kernel consists of two individual convolution kernels: a Path kernel, which captures predicateargument link features, and a Constituent Structure kernel, which captures the syntactic structure features of arguments. Evaluation on the datasets of CoNLL2005 SRL shared task shows that the novel hybrid convolution tree kernel outperforms the previous tree kernels. We also combine our new hybrid tree kernel based method with the standard rich flat feature based method. The experimental results show that the combinational method can get better performance than each of them individually.

• Type: Conference
• Year: 2006
• Where: ACL
• Authors: Wanxiang Che, Min Zhang, Ting Liu, Sheng Li
• Keywords: ACL 2006, ACL 2007, Convolution Tree Kernel, Hybrid Convolution Tree, Tree Kernel