<?xml version="1.0" standalone="yes"?>
<Paper uid="P03-1031">
  <Title>Corpus-based Discourse Understanding in Spoken Dialogue Systems</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2 Discourse Understanding
</SectionTitle>
    <Paragraph position="0"> Here, we describe the basic architecture of a spoken dialogue system (Figure 1). When receiving a user utterance, the system behaves as follows.</Paragraph>
    <Paragraph position="1">  1. The speech recognizer receives a user utterance and outputs a speech recognition hypothesis. 2. The language understanding component re- null ceives the speech recognition hypothesis. The syntactic and semantic analysis is performed to convert it into a form called a dialogue act. Table 1 shows an example of a dialogue act. In the example, &amp;quot;refer-start-and-end-time&amp;quot; is called the dialogue act type, which briefly describes the meaning of a dialogue act, and &amp;quot;start=14:00&amp;quot; and &amp;quot;end=15:00&amp;quot; are add-on information. null  In general, a dialogue act corresponds to one sentence. However, in dialogues where user utterances are unrestricted, smaller units, such as phrases, can be regarded as dialogue acts.  puts the next words to speak. The dialogue state is updated at the same time so that it contains the content of system utterances.</Paragraph>
    <Paragraph position="2"> 5. The speech synthesizer receives the output of the dialogue manager and responds to the user by speech.</Paragraph>
    <Paragraph position="3"> This paper deals with the discourse understanding component. Since we are resolving the ambiguity of speech understanding from the discourse point of view and not within the speech understanding candidates, we assume that a dialogue state is uniquely determined given a dialogue state and the next dialogue act, which means that a dialogue act is a command to change a dialogue state. We also assume that the relationship between the dialogue act and the way to update the dialogue state can be easily described without expertise in dialogue system research. We found that these assumptions are reasonable from our experience in system development. Note also that this paper does not separately deal with reference resolution; we assume that it is performed by a command. A speech understanding result is considered to be equal to a dialogue act in this article.</Paragraph>
    <Paragraph position="4"> In this paper, we consider frames as representations of dialogue states. To represent dialogue states, plans have often been used (Allen and Perrault, 1980; Carberry, 1990). Traditionally, plan-based discourse understanding methods have been implemented mostly in keyboard-based dialogue systems, User Utterance &amp;quot;from two p.m. to three p.m.&amp;quot; Dialogue Act [act-type=refer-start-and-endtime, start=14:00, end=15:00]  alogue act.</Paragraph>
    <Paragraph position="5"> although there are some recent attempts to apply them to spoken dialogue systems as well (Allen et al., 2001; Rich et al., 2001); however, considering the current performance of speech recognizers and the limitations in task domains, we believe frame-based discourse understanding and dialogue management are sufficient (Chu-Carroll, 2000; Seneff, 2002; Bobrow et al., 1977).</Paragraph>
  </Section>
class="xml-element"></Paper>