<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-1050">
  <Title>Kana-Kanji Conversion System with Input Support Based on Prediction</Title>
  <Section position="6" start_page="346" end_page="346" type="concl">
    <SectionTitle>
5 Conclusions
</SectionTitle>
    <Paragraph position="0"> We proposed a l~ana-ka'nji (:onversion system with input sut)port based (m prediction. Ore' system thatures: (i) It; shows prediction cmldid~tes of 1,:a'@i character strings which the 11sev int, ends to input without any special key operation. I\[' no apt)ropriate choice is presented, the candidates disappear automatically when the next l,:a'na character is entered.</Paragraph>
    <Paragraph position="1"> (it) Arbit;rary positions o\[' typed l:ana cJlavacter strillgS are reg~w(le(t as the top of words.</Paragraph>
    <Paragraph position="2"> (iii) A system dietio1~avy and a user dictionary ave used, and each entry in the system (ticLionary has certainty factor calculated :from the frequency of words in corpora.</Paragraph>
    <Paragraph position="3"> (iv) Candidates ave estimated by certainty factor and use.fill.hess factor, and likely ones with greater \['actors than thresholds rare shown.</Paragraph>
    <Paragraph position="4"> (v) ~Zords and phrases are extracted \['rein typed texts, and registered into the user dictionary automatically. null The proposed system could reduce the. user's key input operations to 78% h'om the original ones in the experiments using two kinds of texts. This system was built into the TOSIIIBA Japanese word processor, the JW-8020, which was released in autumn 1.998 (Fig.4).</Paragraph>
    <Paragraph position="5"> To raise a precision by field information and context of texts is our lhtm'e work.</Paragraph>
    <Paragraph position="6"> Figm'e 4.: TOSHIBA Japanese word processor, the JW-8020. where the proposed systenl was built.</Paragraph>
  </Section>
class="xml-element"></Paper>