<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-2193">
  <Title>Learning Tense Translation from Bilingual Corpora</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> A problem for translation is its context dependence. For every ambiguous word, the part of the context relevant for disambiguation must be identified (disambiguation strategy), and every word potentially occurring in this context must be assigned a bias for the translation decision (disambigt, ation information). Manual construction of disambiguation components is quite a chore. Fortunately, the task can be (partly) automated if the tables associating words with biases are learned from a corpus. Statistical approaches also support empirical evaluation of different disambiguation strategies.</Paragraph>
    <Paragraph position="1"> The paper studies disambiguation strategies for tense translation between German and English. The experiments are based on a corpus of appointment scheduling dialogues counting 150,281 German and 154,773 English word tokens aligned in 16,857 turns. The dialogues were recorded, transcribed and translated in the German national Verbmobil project that aims to develop a tri-lingual spoken language translation system. Tense is interesting, since it occurs in nearly every sentence. Tense can be ex* This work was funded by the German Federal Ministry of Education, Science, Research and Technology (BMBF) in the framework of the Verbmobil Project under Grant 01 IV 101 U. Many thanks are due to G. Carroll, hi. Emele, U. Heid and the colleagues in Verbmobil. pressed on the surface lexically as well as morphosyntactically (analytic tenses).</Paragraph>
  </Section>
class="xml-element"></Paper>