<?xml version="1.0" standalone="yes"?>
<Paper uid="H93-1051">
  <Title>CORPUS-BASED STATISTICAL SENSE RESOLUTION</Title>
  <Section position="4" start_page="0" end_page="0" type="relat">
    <SectionTitle>
2. PREVIOUS WORK
</SectionTitle>
    <Paragraph position="0"> Yarowsky \[3\] compared the Bayesian statistical method with the published results of other corpus-based statistical models. Although direct comparison was not possible due to the differences in corpora and evaluation criteria, he minimizes these differences by using the same words, with the same definition of sense. He argues, convincingly, that the Bayesian model is as good as or better than the costlier methods.</Paragraph>
    <Paragraph position="1"> As a pilot for the present study, a two-sense distinction task for line was run using the content vector and neural network classifiers, achieving greater than 90~ accuracy.</Paragraph>
    <Paragraph position="2"> A three-sense distinction task was then run, which is reported in Voorhees, st. al. \[4\], and discussed in Section 5.</Paragraph>
  </Section>
class="xml-element"></Paper>