<?xml version="1.0" standalone="yes"?>
<Paper uid="H92-1045">
  <Title>tion Using Statistical Models of Roget's Categories</Title>
  <Section position="6" start_page="236" end_page="236" type="concl">
    <SectionTitle>
5. CONCLUSION
</SectionTitle>
    <Paragraph position="0"> In conclusion, it appears that our hypothesis is correct; well-written discourses tend to avoid multiple senses of a polysemous word. This result can be used in two basic ways: (1) as an additional source of constraint for improving the performance of a word-sense disambiguation algorithm, and (2) as an aide in collecting annotated test materials for evaluating disamhiguation algorithms.</Paragraph>
  </Section>
class="xml-element"></Paper>