<?xml version="1.0" standalone="yes"?>
<Paper uid="C92-2101">
  <Title>LEARNING TRANSLATION TEMPLATES FROM BILINGUAL TEXT</Title>
  <Section position="8" start_page="0" end_page="0" type="concl">
    <SectionTitle>
7. Conclusion
</SectionTitle>
    <Paragraph position="0"> We have developed an algorithm for learning translation templates from translation examples. A translation template is a bilingual pair of sentences in which corresponding units are coupled and replaced with variables. Correspondence between units is reliably identified by using a bilingual dictionary and the results of syntactic analysis of the sentences. Syntactic ambiguity and ambiguity in correspondence between units are simultaneously resolved. All translation templates generated from a bilingual corpus are grouped by their source language part, and they are then further refined to resolve conflicts among templates whose source language parts are the same but whose target language parts are different.</Paragraph>
    <Paragraph position="1"> This algorithm makes it possible to effectively extract a variety of knowledge from a bilingual corpus.</Paragraph>
    <Paragraph position="2"> Not only is the quality of translations improved, but machine translation systems can be easily customized.</Paragraph>
  </Section>
class="xml-element"></Paper>