<?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="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> In this paper we describe the function and design of the robust semantic processing component which we are currently developing in the context of the Verbmobil speech translation project. We aim at improving the system's performance in terms of coverage and quality of translations by combining fragmentary analyses when no spanning analysis of the input can be derived because of spontaneous speech phenomena or speech recognition errors.</Paragraph>
  </Section>
class="xml-element"></Paper>