<?xml version="1.0" standalone="yes"?>
<Paper uid="P93-1024">
  <Title>DISTRIBUTIONAL CLUSTERING OF ENGLISH WORDS</Title>
  <Section position="7" start_page="189" end_page="189" type="concl">
    <SectionTitle>
CONCLUSIONS
</SectionTitle>
    <Paragraph position="0"> We have demonstrated that a general divisive clustering procedure for probability distributions can be used to group words according to their participation in particular grammatical relations with other words. The resulting clusters are intuitively informative, and can be used to construct class-based word coocurrence models with substantial predictive power.</Paragraph>
    <Paragraph position="1"> While the clusters derived by the proposed method seem in many cases semantically significant, this intuition needs to be grounded in a more rigorous assessment. In addition to predictive power evaluations of the kind we have already carried out, it might be worth comparing automatically-derived clusters with human judge: ments in a suitable experimental setting.</Paragraph>
    <Paragraph position="2"> Moving further in the direction of class-based language models, we plan to consider additional distributional relations (for instance, adjectivenoun) and apply the results of clustering to the grouping of lexical associations in lexicalized grammar frameworks such as stochastic lexicalized tree-adjoining grammars (Schabes, 1992).</Paragraph>
  </Section>
class="xml-element"></Paper>