<?xml version="1.0" standalone="yes"?>
<Paper uid="P04-1061">
  <Title>Corpus-Based Induction of Syntactic Structure: Models of Dependency and Constituency</Title>
  <Section position="7" start_page="0" end_page="0" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have presented a successful new dependency-based model for the unsupervised induction of syntactic structure, which picks up the key ideas that have made dependency models successful in supervised statistical parsing work. We proceeded to show that it works cross-linguistically. We then demonstrated how this model could be combined with the previous best constituent-induction model to produce a combination which, in general, substantially outperforms either individual model, on either metric. A key reason that these models are capable of recovering structure more accurately than previous work is that they minimize the amount of hidden structure that must be induced. In particular, neither model attempts to learn intermediate, recursive categories with no direct connection to surface statistics. Our results here are just on the ungrounded induction of syntactic structure. Nonetheless, we see the investigation of what patterns can be recovered from corpora as important, both from a computational perspective and from a philosophical one. It demonstrates that the broad constituent and dependency structure of a language can be recovered quite successfully (individually or, more effectively, jointly) from a very modest amount of training data.</Paragraph>
  </Section>
class="xml-element"></Paper>