<?xml version="1.0" standalone="yes"?>
<Paper uid="H94-1025">
  <Title>Building Japanese-English Dictionary based on Ontology for Machine Translation</Title>
  <Section position="5" start_page="143" end_page="144" type="evalu">
    <SectionTitle>
4. Results
</SectionTitle>
    <Paragraph position="0"> We simulated these algorithms for 980 nouns, 860 verbs and 520 adjectives in a preliminary experiment. Half of the words belong to case-II and the other half to case-IV. The algorithms are applied according to the following procedure:  (Examples &amp;quot;deposit money in a bank&amp;quot; &amp;quot;have a bank account of 1,000,000 yen&amp;quot; &amp;quot;open an account with a bank&amp;quot;))</Paragraph>
    <Paragraph position="2"> The equivalent-word match is applied to case-ll words. The results of the equivalent-word match are in Table 1.</Paragraph>
    <Paragraph position="3"> The argument match is applied to all words except for the ones correctly determined by the equivalent-word match. The accuracy of the equivalent-word match and the argument match is in Table 2.</Paragraph>
    <Paragraph position="4"> The example match is applied to all words except for the ones correctly determined by the above two matches. The total accuracy of the three matches  * Correct: The highest confidence is assigned to all the correct concepts.</Paragraph>
    <Paragraph position="5"> * Close: The highest confidence is assigned to some of the correct concepts.</Paragraph>
    <Paragraph position="6"> * Open: No confidence value is assigned to the correct concepts.</Paragraph>
    <Paragraph position="7">  The algorithms are found to be effective for more than 80% of the words, thereby helping to reduce the dictionary development costs of human workers.</Paragraph>
  </Section>
class="xml-element"></Paper>