<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-0717">
  <Title>Inducing Syntactic Categories by Context Distribution Clustering</Title>
  <Section position="8" start_page="92" end_page="93" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> The work of Chater and Finch can be seen as similar to the work presented here given an independence assumption. We can model the context distribution as being the product of independent distributions for each relative position; in this case the KL divergence is the sum of the divergences for each independent distribution. This independence assumption is most clearly false when the word is ambiguous; this perhaps explains the poor performance of these algorithms with ambiguous words. The new algorithm currently does not use information  about the orthography of the word, an important source of information. In future work, I will integrate this with a morphology-learning program. I am currently applying this approach to the induction of phrase structure rules, and preliminary experiments have shown encouraging results.</Paragraph>
    <Paragraph position="1"> In summary, the new method avoids the limitations of other approaches, and is better suited to integration into a complete unsupervised language acquisition system.</Paragraph>
  </Section>
class="xml-element"></Paper>