<?xml version="1.0" standalone="yes"?>
<Paper uid="A97-1008">
  <Title>An Evaluation of Strategies for Selective Utterance Verification for Spoken Natural Language Dialog</Title>
  <Section position="7" start_page="45" end_page="46" type="evalu">
    <SectionTitle>
ELSE
</SectionTitle>
    <Paragraph position="0"> engage in a verification suhdialog Using this decision rule, the over-verification rate rises to 31.8% while the under-verification rate falls to 1.4%. Although it significantly reduces the under-verification rate, this strategy clearly leads to an ex- null cessive number of over-verifications. We next consider combination strategies that look at both parse cost and context.</Paragraph>
    <Section position="1" start_page="46" end_page="46" type="sub_section">
      <SectionTitle>
4.3 Strategy 3: Parse Cost/Context
Combination
</SectionTitle>
      <Paragraph position="0"> The Strategy 1 decision rule for utterance verification says to engage in a verification subdialog if the parser confidence value falls below the verification threshold. With context-dependent verification we additionally require that the utterance meaning cannot be part of the main expectation. Thus, the decision rule for verification may be revised as follows:</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>