Rencently there have been a revived interst in semantic parsing by pplying statistical and machine learning methods to semantically annotated corpora such as the FrameNet and the Proposition Bank. So far much of the research has been focused on English due to the lack of semantically annotated resources in other languages, such as Chinese. In this paper, we use the convolution tree kernel to decompose these larger structure features and compute the kernel function in polynomial time. This paper provides hybrid convolution tree kernel to make fusion different convolution tree kernels, which can model different features with different kernels. The eventuation results show that the novel method is better than the traditional convolution tree kernel. © 2012 Springer-Verlag GmbH Berlin Heidelberg.
CITATION STYLE
Wang, C., & Ge, J. (2012). Chinese semantic role labeling based on the hybrid convolution tree kernel. Advances in Intelligent and Soft Computing, 136, 479–486. https://doi.org/10.1007/978-3-642-27711-5_64
Mendeley helps you to discover research relevant for your work.