<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-1082">
  <Title>Bunsetsu Identification Using Category-Exclusive Rules</Title>
  <Section position="5" start_page="570" end_page="570" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> To solve tile t)roblem of aecm'ate btmsetsu identification, we carried out ext)eriments comt)aring tbur existing machine-learning methods (decisiontree method, maxilnum-entrol)y method, examI)le-based method and decision-list method). We obtained the following order of acem'acy in bunsetsu identification.</Paragraph>
    <Paragraph position="2"> Maximum Entropy &gt; Decision Tree We also described a new method which uses category-exclusive rules with the highest similarity. This method performed better than the other learning methods in ore&amp;quot; exi)eriments.</Paragraph>
    <Paragraph position="3"> (&gt;l'his work used oifly the POS information of the two roof phemes of an analyzed space.</Paragraph>
  </Section>
class="xml-element"></Paper>