<?xml version="1.0" standalone="yes"?>
<Paper uid="W04-0819">
  <Title>Semantic Parsing Based on FrameNet</Title>
  <Section position="11" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> In this paper we describe a method for automatically labeling semantic roles based on support vector machines (SVMs). The training benefits from an extended data set on which multi-class classifiers were derived. The polynomial kernel of the SVMs enable the combination of four feature sets that produced very good results both for the Restricted Case and the Unrestricted Case. The paper also describes some heuristics for mapping syntactic constituents onto FEs.</Paragraph>
  </Section>
class="xml-element"></Paper>