<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-2118">
  <Title>An ascription-based approach to Speech Acts</Title>
  <Section position="4" start_page="703" end_page="703" type="concl">
    <SectionTitle>
5. Conclusions and future work
</SectionTitle>
    <Paragraph position="0"> We have argued that the computation of highly nested belief structures during the performance or recognition of a speech act is implausible. In particular, the concept of mutual belief seems too strong. Instead, we have put forward a theory of speech acts where only the minimal set of beliefs is ascribed at the time of the utterance. If further belief nestings are required then they can be derived using belief ascription techniques as required.</Paragraph>
    <Paragraph position="1"> We believe that, for the most part, during normal dialogue, the minimal effects of any speech act are all that are required. However, our approach allows highly nested belief structures to be computed on demand if required, for example, to understand non-conventional language use.</Paragraph>
    <Paragraph position="2"> Future work includes the attachment of a robust dialogue parser. We also intend to link ViewGen to the LaSie information extraction platform (Gaizaukas et al, 1995) so as to develop a testable belief set empirically derived from a small medical domain corpus.</Paragraph>
  </Section>
class="xml-element"></Paper>