<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-2193">
  <Title>Learning Tense Translation from Bilingual Corpora</Title>
  <Section position="9" start_page="1186" end_page="1186" type="concl">
    <SectionTitle>
5 Conclusion
</SectionTitle>
    <Paragraph position="0"> The paper presents a way to test disambiguation strategies on real data and to measure the influence of diverse factors ranging from sentence internal context to the choice of representation. The pertaining disambiguation information learned from the corpus is put into action in the symbolic transfer component of the Verbmobil system (Dorna and Emele, 1996).</Paragraph>
    <Paragraph position="1"> The only other empirical study of tense translation (Santos, 1994) I am aware of was conducted on a manually annotated Portuguese-English corpus (48,607 English, 43,492 Portuguese word tokens and 6,334 tense translation pairs). It neither gives results for all tenses nor considers disambiguation factors. Still, it acknowledges the surprising divergence of tense across languages and argues against the widely held belief that surface tenses can be mapped directly into an interlingual representation. Although the findings reported here support this conclusion, it should be noted that a bilingual corpus can only give one of several possible translations.</Paragraph>
  </Section>
class="xml-element"></Paper>