<?xml version="1.0" standalone="yes"?>
<Paper uid="H01-1023">
  <Title>Evaluation Results for the Talk'n'Travel System</Title>
  <Section position="3" start_page="0" end_page="0" type="metho">
    <SectionTitle>
2. SYSTEM OVERVIEW
</SectionTitle>
    <Paragraph position="0"> The figure shows a block diagram of Talk'n'Travel. Spoken language understanding is provided by statistical N-gram speech recognition and a robust language understanding component. A plan-based dialogue manager coordinates interaction with the user, handling unexpected user input more flexibly than conventional finite-state dialogue control networks. It works in tandem with a state management component that adjusts the current model of user intention based on the user's last utterance in context.</Paragraph>
    <Paragraph position="1"> Meaning and task state are represented by the path constraint representation (Stallard, 2000). An inference component is included which allows the system to deduce implicit requirements from explicit statements by the user, and to retract them if the premises change.</Paragraph>
    <Paragraph position="2"> The system is interfaced to the Yahoo/Travelocity flight schedule website, for access to live flight schedule information. Queries to the website are spawned off in a separate thread, which the dialogue manager monitors ands reports on to the user.</Paragraph>
  </Section>
  <Section position="4" start_page="0" end_page="0" type="metho">
    <SectionTitle>
3. DIALOGUE STRATEGY
</SectionTitle>
    <Paragraph position="0"> Talk'n'Travel employs both open-ended and directed prompts.</Paragraph>
    <Paragraph position="1"> Sessions begin with open prompts like &amp;quot;What trip would you to take?&amp;quot;. The system then goes to directed prompts to get any information the user did not provide (&amp;quot;What day are you leaving?&amp;quot;, etc). The user may give arbitrary information at any prompt, however. The system provides implicit confirmation of the change in task state caused by the user's last utterance (&amp;quot;Flying from Boston to Denver tomorrow &amp;quot;) to ensure mutual understanding.</Paragraph>
    <Paragraph position="2"> The system seeks explicit confirmation in certain cases, for example where the user appears to be making a change in date of travel. Once sufficient information is obtained, the system offers a set of candidate flights, one at a time, for the user to accept or reject.</Paragraph>
  </Section>
class="xml-element"></Paper>