<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-2107">
  <Title>Statistical Method of Recognizing Local Cohesion in Spoken Dialogues</Title>
  <Section position="5" start_page="637" end_page="638" type="evalu">
    <SectionTitle>
4 Experiments
</SectionTitle>
    <Paragraph position="0"> A series of experiments was done to evaluate our method. The experiments were carried out to decide whether one utterance and the next one have local cohesion with each other or not. The results of the experiment were able to segment a dialogue into several subdialogues.</Paragraph>
    <Paragraph position="1"> First, Set-ENDEXPR was constructed automatically by our extraction method for fixed expressions from the ATR speech and language database \[Morimoto 94\]. The database includes about 600 task-oriented dialogues concerned with several domains, such as hotel reservation, flight cancellation and so on and each of the dialogues includes about 50 utterances on average. We have extracted about one hundred fixed-expressions from the database by the extraction method. Table  the end of expressions (speech act type)</Paragraph>
    <Paragraph position="3"> Secondly, we chose 60 dialogues from the ATR database and annotated them with local cohesion by hand-code such as that shown in Figure 1 in Section 2. Then, six dialogues were taken from the 60 dialogues to use in testing for the open data, and the rest of the dialogues (54 dialogues) were used to calculate ENDEXPR bigrams. Moreover, six dialogues were taken from the 54 dialogues for the closed data. Using the 54 dialogues, the ENDEXPR bigrams were produced in the following four parts: An ENDEXPR bigram part A : with local cohesion + turn-taking.</Paragraph>
    <Paragraph position="4"> part B : with local cohesion + no turn-taking.</Paragraph>
    <Paragraph position="5"> part C : without local cohesion + turn-taking.</Paragraph>
    <Paragraph position="6"> part D : without local cohesion + no turn-taking. where &amp;quot;turn-taking&amp;quot; means that an utterance and the next one are produced by different persons and &amp;quot;no turn-taking&amp;quot; means that they are done by the same person.</Paragraph>
    <Paragraph position="7"> Table 2 shows examples of ENDEXPR bigrams with local cohesion.</Paragraph>
    <Paragraph position="8"> with local cohesion + turn-taking (part A)  Using these ENDEXPR bigrams, a series of experiments was done for the closed data. and the open data. In the experiments, we defined the two utterances with local cohesion, if they had the plausibility above a certain threshold, and we chose Smoothing Method 1 under the condition</Paragraph>
    <Paragraph position="10"> Table 3 shows the accuracy of recognizing local cohesion in three cases: the turn-taking case, the no turn-taking case and the total case.</Paragraph>
    <Paragraph position="11">  In Table 3, the &amp;quot;default method&amp;quot; assumed that all of the pairs of utterances in a dialogue has local cohesion, and the accuracy was calculated as: The accuracy in the &amp;quot;default method&amp;quot; The number of the pairs of utterances . wltn local coneston = The total number of the pairs of utterances in a dialogue As shown in Table 3, the accuracy of our method was higher than that of the &amp;quot;default method&amp;quot;. Using the smoothing method, we obtained a 93.8% accuracy for the closed data and about a 78.4% accuracy for the open data.</Paragraph>
  </Section>
class="xml-element"></Paper>