<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-2236">
  <Title>Automatic Construction of Frame Representations for Spontaneous Speech in Unrestricted Domains</Title>
  <Section position="8" start_page="1449" end_page="1451" type="concl">
    <SectionTitle>
6 Summary
</SectionTitle>
    <Paragraph position="0"> We have presented a system which is able to build shallow semantic representations for spontaneous speech in unrestricted domains, without the necessity of extensive knowledge engineering.</Paragraph>
    <Paragraph position="1"> Initial experiments demonstrate that this approach is feasible in principle. However, more work to improve the major components is needed to reach a more reliable and valid output.</Paragraph>
    <Paragraph position="2"> The potentials of this approach for NLP applications that use speech as their input are obvious: semantic representations can enhance almost all tasks that so far have either been restricted to narrow domains or were mainly using word-level representations, such as text summarization, information retrieval, or shallow machine translation.</Paragraph>
    <Paragraph position="3"> 11 Sometimes, the speech acts will span more than one short clause but as long as the turn-boundaries are fixed for both our system and the speech act classifier, the re-combination of short clauses can be done straightforwardly.</Paragraph>
  </Section>
class="xml-element"></Paper>