<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-0508">
  <Title>Stochastic Finite-State models for Spoken Language Machine ': anslation</Title>
  <Section position="8" start_page="56" end_page="56" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have presented an architecture for speech translation in limited domains based on the simple machinery of stochastic finite-state transducers. We have implemented stochastic finite-state models for English-Japanese and Japanese-English translation in limited domains. These models have been trained automatically from source-target utterance pairs.</Paragraph>
    <Paragraph position="1"> We have evaluated the effectiveness of such a translation model in the context of a call-type classification task.</Paragraph>
  </Section>
class="xml-element"></Paper>