<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-2107">
  <Title>Statistical Method of Recognizing Local Cohesion in Spoken Dialogues</Title>
  <Section position="2" start_page="0" end_page="634" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> For ambiguity resolution, processing of a discourse structure is one of the important processes in Natural Language Processing (NLP). Indeed, discourse structures play a useful role in speech recognition, which is an application of NLP. In the case of Japanese, it is very difficult to recognize the end in utterances by using current speech recognition techniques because the sound power of an ending tends to be small. For example, &amp;quot;desu&amp;quot;, which represents the speech act type &amp;quot;response&amp;quot;, is often misrecognized as &amp;quot;desu-ka (question)&amp;quot; or &amp;quot;desu-ne (confirmation)&amp;quot;. On the other hand, Japanese can easily select the adequate expression &amp;quot;desu&amp;quot;, when the intention of the previous utterance is concerned with a question. This is because they use the coherence relation (local cohesion) between the two utterances, question-response.</Paragraph>
    <Paragraph position="1"> In the conventional approach (i.e., rule-based approach) to processing the discourse structure \[Hauptmann 88\]\[Kudo 90\]\[Yamaoka 91\]\[Young 91\], NLP engineers built discourse knowledge by hand-coding. However, the rule-based approach has a bottleneck in that it is a hard job to add discourse knowledge when the employed NLP system deals with a larger domain and more vocabulary.</Paragraph>
    <Paragraph position="2"> Recently, statistical approaches have been attracting attention for their ability to acquire linguistic knowledge from a corpus. Compared with the above rule-based approach, a statistical approach is easy to apply to larger domains since the linguistic knowledge can be automatically extracted from the corpora concerned with the domain. However, little research has been reported in discourse processing \[Nagata 94\]\[Reithinger 95\], while in the areas of morphological analysis and syntactic analysis, many research studies have been proposed in recent years.</Paragraph>
    <Paragraph position="3"> This paper presents a method for automatically recognizing local cohesion between utterances, which is one of the discourse structures in task-oriented spoken dialogues. We can automatically acquire discourse knowledge from an annotated corpus with local cohesion. In this paper we focus on speech act type-based local cohesion.</Paragraph>
    <Paragraph position="4"> The presented method consists of two steps ~1) identifying the speech act expressions in an utterance and 2) calculating the plausibility of local cohesion between the speech act expressions by using the dialogue corpus annotated with local cohesion. We present two methods of interpolating the plausibility of local cohesion based on surface information on utterances. Our method has obtained a 93% accuracy for closed data and a 78% accuracy for open data in recognizing a pair of utterances with local cohesion.</Paragraph>
    <Paragraph position="5"> In Section 2, local cohesion in task-oriented dialogues is described. In Section 3, our statistical method is presented. In Section 4, the results of a series of experiments using our method are described. null</Paragraph>
  </Section>
class="xml-element"></Paper>