<?xml version="1.0" standalone="yes"?>
<Paper uid="W05-0407">
  <Title>Engineering of Syntactic Features for Shallow Semantic Parsing</Title>
  <Section position="7" start_page="54" end_page="54" type="concl">
    <SectionTitle>
7 Conclusions
</SectionTitle>
    <Paragraph position="0"> The feature design for new natural language learning tasks is difficult. We can take advantage from the kernel methods to model our intuitive knowledge about the target linguistic phenomenon. In this paper we have shown that we can exploit the properties of tree kernels to engineer syntactic features for the predicate argument boundary detection task.</Paragraph>
    <Paragraph position="1"> Preliminary results on gold standard trees suggest that (1) the information related to the whole predicate argument structure is important and (2) tree kernel can be used to generate syntactic features.</Paragraph>
    <Paragraph position="2"> In the future, we would like to use an approach similar to the PAST classifier on parses provided by different parsing models to detect boundary and to classify semantic role more accurately .</Paragraph>
  </Section>
class="xml-element"></Paper>