<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-2174">
  <Title>Chinese Generation in a Spoken Dialogue Translation System</Title>
  <Section position="6" start_page="1144" end_page="1144" type="evalu">
    <SectionTitle>
5. Results
</SectionTitle>
    <Paragraph position="0"> The current version of the system has been tested on our hotel reservation corpus (Chengqing Zong, 1999). The whole corpus includes about 90 dialogues, annotated by hand with underspecificd semantic representation. I1 contains about 3000 USRs. Now we have 23 speech acls and about 60 concepts in lhe corpus.</Paragraph>
    <Paragraph position="1"> The generation lnodulc is tested on all sentences in the corpus. And 90% of the generated sentences arc rated as grammatically and semantically correct. The other 10% are rated as wrong because the mood of the sentences is not conect. This is mainly caused by the lack of the dialogue context.</Paragraph>
  </Section>
class="xml-element"></Paper>