<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-1052">
  <Title>A Computational Model of Incremental Utterance Production in Task-Oriented Dialogues</Title>
  <Section position="12" start_page="307" end_page="308" type="evalu">
    <SectionTitle>
8 Experiments
</SectionTitle>
    <Paragraph position="0"> This model has been implemented in Common Lisp. A logical constraint unification systern (Nakano 1991) is used in the planners. The domain planner includes 18 action schemata and 16 decomposition methods. The utterance plan- null ner includes 16 action schemata and 16 decomposition methods. We ewduated pragmatic constraints in an utterance simulation experiment, where discourses generate.d with the constraints were contpared with those generated without them. A map including 120 h)cations such as station and 25 railroad lines w~s used. The pause length limit was ().5 see.</Paragraph>
    <Paragraph position="1"> When pragmatic constraints were used, this implemented systeIn generated relevant discourses. Figure 6 shows the discourse generated when the problem of inoving frolIl the Mus~ksliino Center to the Atsugi Center was given. Filler terms such as gto were produced to satisfy the time constraints. Pragmatic constraint (el) was used ill (e2), ~Uq explained in section 7.4. Constraint (c2) was used to zero-proImminalize stations in the focus of attention. Constraint (e3) was used in ((:1) to topicalize the Musashino Center. Topicalization was also used in other cases where the system must shift the focus of attention to the location already described in the preceding discourse. Such cases happened when the system started utterantes based on an abstract domain I)lan, took a long time to obtain a more concrete plan, and then elaborated on a route from a location that was not in focus based on the concrete plan. Without prt~gmatic constraints, the system generated irrelevant and excessively redundant discourses.</Paragraph>
  </Section>
class="xml-element"></Paper>