<?xml version="1.0" standalone="yes"?>
<Paper uid="P06-2010">
  <Title>Sydney, July 2006. c(c)2006 Association for Computational Linguistics A Hybrid Convolution Tree Kernel for Semantic Role Labeling</Title>
  <Section position="8" start_page="78" end_page="79" type="concl">
    <SectionTitle>
6 Conclusions and Future Work
</SectionTitle>
    <Paragraph position="0"> In this paper we proposed the hybrid convolution kernel to model syntactic structure information for SRL. Different from the previous convolution tree kernel based methods, our contribution  on the WSJ test (bottom).</Paragraph>
    <Paragraph position="1"> is that we distinguish between the Path and the Constituent Structure feature spaces. Evaluation on the datasets of CoNLL-2005 SRL shared task, shows that our novel hybrid convolution tree kernel outperforms the PAF kernel method. Although the hybrid kernel base method is not as good as the standard rich flat feature based methods, it can improve the state of the art feature-based methods by implicating the more generalizing syntactic information. null Kernel-based methods provide a good framework to use some features which are difficult to model in the standard flat feature based methods. For example the semantic similarity of words can be used in kernels well. We can use general purpose corpus to create clusters of similar words or use available resources like WordNet. We can also use the hybrid kernel method into other tasks, such as relation extraction in the future.</Paragraph>
  </Section>
class="xml-element"></Paper>