<?xml version="1.0" standalone="yes"?>
<Paper uid="P99-1036">
  <Title>A Part of Speech Estimation Method for Japanese Unknown Words using a Statistical Model of Morphology and Context</Title>
  <Section position="9" start_page="283" end_page="283" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> We present a statistical model of Japanese unknown words using word morphology and word context. We find that Japanese words are better modeled by classifying words based on the character sets (kanji, hiragana, katakana, etc.) and its changes. This is because the different character sets behave differently in many ways (historical etymology, ideogram vs. phonogram, etc.). Both word segmentation accuracy and part of speech tagging accuracy are improved by treating them differently.</Paragraph>
  </Section>
class="xml-element"></Paper>