<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-2229">
  <Title>A Model for Robust Processing of Spontaneous Speech by Integrating Viable Fragments*</Title>
  <Section position="9" start_page="1406" end_page="1406" type="concl">
    <SectionTitle>
7 Conclusion and Outlook
</SectionTitle>
    <Paragraph position="0"> We have described a model for the combination of partial parsing results and how it can be applied in order to improve the robustness of a speech processing system. A prototype version was integrated into the Verbmobil system in autumn 1997 and is currently being extended.</Paragraph>
    <Paragraph position="1"> We are working on improving the selection of resuits by using a stochastic model of V1T sequence probabilities, on the extension of the rule set to cover more spontaneous speech phenomena of German, English and Japanese, and on refining the mechanism for extending active edges to arrive at a spanning analyses.</Paragraph>
  </Section>
class="xml-element"></Paper>