论文信息 - Fast Computing Grammar-driven Convolution Tree Kernel for Semantic Role Labeling

Fast Computing Grammar-driven Convolution Tree Kernel for Semantic Role Labeling

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.

[1] Daniel Gildea,et al. The Necessity of Parsing for Predicate Argument Recognition , 2002, ACL.

[2] Dan Roth,et al. The Necessity of Syntactic Parsing for Semantic Role Labeling , 2005, IJCAI.

[3] Guodong Zhou,et al. A Grammar-driven Convolution Tree Kernel for Semantic Role Classification , 2007, ACL.

[4] Wanxiang Che,et al. A Hybrid Convolution Tree Kernel for Semantic Role Labeling , 2006, ACL.

[5] Alessandro Moschitti. Syntactic Kernels for Natural Language Learning: the Semantic Role Labeling Case , 2006, HLT-NAACL.

[6] Xavier Carreras,et al. Introduction to the CoNLL-2005 Shared Task: Semantic Role Labeling , 2005, CoNLL.

[7] Michael Collins,et al. Convolution Kernels for Natural Language , 2001, NIPS.

[8] Thorsten Joachims,et al. Learning to classify text using support vector machines - methods, theory and algorithms , 2002, The Kluwer international series in engineering and computer science.

[9] Alessandro Moschitti,et al. A Study on Convolution Kernels for Shallow Statistic Parsing , 2004, ACL.

[10] Vladimir Vapnik,et al. Statistical learning theory , 1998 .

[11] Nello Cristianini,et al. Classification using String Kernels , 2000 .