<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-2139">
  <Title>Analysis of Japanese Compound Nouns using Collocational Information</Title>
  <Section position="8" start_page="868" end_page="868" type="concl">
    <SectionTitle>
5 Concluding Remarks
</SectionTitle>
    <Paragraph position="0"> We propose a method to analyze Japanese compound nouns using collocational information and a thesaurus. Wc also describe a method to a(:quire the collocational information from a corpus of four kauzi character words. The method to acquire collocational information is dependent on the Japanese character, but the method to calculate preferences of structures si applicat)le to any languagc with comlmund nouns.</Paragraph>
    <Paragraph position="1"> The experiments show that whcn the method anMyzes compound nouns with an average length 4.9, it produces an accuracy rate of about 83%.</Paragraph>
    <Paragraph position="2"> We are considering those future works that follow: null , incorl)orate other syntactic information, such as affixes knowledge * use another semantic information as well as thesauruses, such as sclcctional restriction * apply this method to disambiguate other syntactic structures such as dependency relations</Paragraph>
  </Section>
class="xml-element"></Paper>