<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-2116">
  <Title>VERBAL CASL FRAME ACQUISITION FROM A BIIAN(?,UAL C()RPUS: GRADUAL KNOWI,EDGE ACQUISITION</Title>
  <Section position="13" start_page="730" end_page="730" type="concl">
    <SectionTitle>
6 Conclusion
</SectionTitle>
    <Paragraph position="0"> We proposed the idea ef gradual knowledge acquisition from a bilingual corpus. The knowledge addressed in this paper was the surface verbal case frames for the Japanese translation of English verbs. The process consists of three steps: corpus construction, data conversion, and maclfine learning.</Paragraph>
    <Paragraph position="1"> The case-fiame trees we obtained were highly intelligible: they can be interpreted from the linguistic viewpoint, They basically matclled linguistic intttition and more precise knowledge was sometimes acquired. Tree analysis showed that in some cases comlllementary learning occurred even wllen neccssmy knowledge was nol awlilable.</Paragraph>
    <Paragraph position="2"> The trees successfully distinguislled tile translations of the training data.</Paragraph>
    <Paragraph position="3"> Our approach basically fulfills our primary goal: acquit'ing detailed knowledge and accunltdating it in a way that is consistent and unambiguous.</Paragraph>
    <Paragraph position="4"> There are several areas for future work. The work in lhis paper used tile word forms as tile restrictions for tile case categories, resulting ill case-frame trees with limited trauslation power for open dala. To increase the lranslation power, we are generalizing the corllus by using semanlic codes and plan to produce case-frame trees with thenl.</Paragraph>
  </Section>
class="xml-element"></Paper>