<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-1420">
  <Title>Multilingual Summary Generation in a Speech-To-Speech Translation System for Multilingual Dialogues*</Title>
  <Section position="9" start_page="153" end_page="153" type="concl">
    <SectionTitle>
7 Conclusion
</SectionTitle>
    <Paragraph position="0"> We have presented an extension to existing modules allowing for the generation of summaries within the VERBMOBIL system. To our knowledge our system is the only one that uses semantic representation as basis for summarizing. Other approaches use, e.g., statistical techniques or rhetorical parsing (Waibel et al., 1998; Hovy and Marcu, 1998) to obtain the summaries. Moreover, although our module is restricted to language specific processing, the use of semantics and the transfer module allow for the generation of multilingual documents in a very straight-forward fashion.</Paragraph>
    <Paragraph position="1"> In the near future we will extend the system with respect to: o Sentence Split At present the first found sentence split is chosen. This is not necessarily the optimal one. We are currently in the process of developing criteria for ranking competing results.</Paragraph>
    <Paragraph position="2"> o Japanese The VERBMOBIL system currently includes German, English and Japanese. We intend to apply the same technique as for the English summaries to generate Japanese ones.</Paragraph>
  </Section>
class="xml-element"></Paper>