<?xml version="1.0" standalone="yes"?>
<Paper uid="W06-2927">
  <Title>Multi-lingual Dependency Parsing at NAIST</Title>
  <Section position="7" start_page="194" end_page="194" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> This paper reported on multi-lingual dependency parsing on combining SVMs and MaxEnt. The system uses SVMs for word dependency attachment analysis and MaxEnt for the label tagging when the new dependency attachment is generated.</Paragraph>
    <Paragraph position="1"> We discussed some preprocessing methods that are useful in our preceding work for Chinese dependency analysis, but these methods, except one, cannot be used in multi-lingual dependency parsing.</Paragraph>
    <Paragraph position="2"> Only using the SVM-based tagger to extract the neighbor relation could improve many languages in our experiment, therefore we use the tagger in the parser as its preprocessing.</Paragraph>
  </Section>
class="xml-element"></Paper>