<?xml version="1.0" standalone="yes"?>
<Paper uid="P96-1044">
  <Title>Linguistic Structure as Composition and Perturbation</Title>
  <Section position="9" start_page="339" end_page="340" type="concl">
    <SectionTitle>
7 Conclusions
</SectionTitle>
    <Paragraph position="0"> No previous unsupervised language-learning procedure has produced structures that match so closely with linguistic intuitions. We take this as a vindication of the perturbation-of-compositions representation. Its ability to capture the statistical and linguistic idiosyncrasies of large structures without sac- null rificing the obvious regularities within them makes it a valuable tool for a wide variety of induction problems. null</Paragraph>
  </Section>
class="xml-element"></Paper>