<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-2164">
  <Title>A GRAMMAR AND A PARSER FOR SPONTANEOUS SPEECH</Title>
  <Section position="3" start_page="0" end_page="1014" type="intro">
    <SectionTitle>
1 INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> Most dialogue understanding studies have focused on the mental states, plans, and intentions of the participants (Cohen et al., 1990). These studies have presumed that utterances can be analyzed syntactically and semantically and that the representation of the speech acts performed by those ntterances can be obtained. Spontaneonsly spoken utterances differ considerably from written sentences, however, so it is not possible to analyze them syntactically and semantically when using a grammar for written sentences.</Paragraph>
    <Paragraph position="1"> Spontaneous speech, a sequence of spontaneously spoken utterances, can be distinguished from wellplanned utterances like radio news and movie dialogues. Mnch effort has been put into incorporating grammatical information into speech mlderstanding (e.g., Hayes et el. (1986), Young et al. (1989), Okada (1991)), but because this work has focused on wellplanned utterances, spontaneously spoken utterances have received little attention. This has partly been due to the lack of a grammar and processing technique that can be applied to spontaneous speech. Consequently, to attain an understanding of dialogues it is necessary to develop a way to analyze spontaneous speech syntactically and semantically.</Paragraph>
    <Paragraph position="2"> There are two approaches to developing this kind of analysis method: one is to develop a grammar and analysis method for spontaneous speech that do not depend on syntactic constraints as much as the conventional methods for written sentences do (Den, 1993), and the other is to augment the grammar used for written sentences and modify the conventional analysis method to deal with spontaneous speech.</Paragraph>
    <Paragraph position="3"> The former method would fail, however, when new information is conveyed in the utterances; that is, when the semantic characteristics of the dialogue topic are not known to the hearer. In such cases, even ill a dialogue, the syntactic constraints are nsed for understanding utterances. Because methods that disregard syntactic constraints would not work well in these kinds of cases, we took the latter approach.</Paragraph>
    <Paragraph position="4"> We analyzed more than a hundred dialogue transcripts and classified the distinctive phenomena in spontaneous Japanese speech. To handle those phenomena, we develop a computational model called L'nsemble Model (Shimazu et al., 1993b), in which syntactic, semantic, and pragmatic processing modules and modules that do combination of some or all of those processing analyze the input in i)arallel and independently. Even if some of the modules are unable to analyze the input, the other modules still output their results. This mode\] can handle various kinds of irregular expressions, such as case particle omission, inversions, and fragmentary expressions.</Paragraph>
    <Paragraph position="5"> We also developed Grass-.\] ( GT&amp;quot;ammar for spontaneous speech in Japanese), which enables the syntactic and semantic processing modules of t~he Ensemble Model to deal with some of the phenomena peculiar to spontaneous speech. Since G~'ass-.\] is an augmentation of a grammar used to analyze written sentences (Grat-J, Gr'ammar for lexts in Japanese), Crass-Y-based parsers can be used for syntactically complex utterances.</Paragraph>
    <Paragraph position="6"> There are two distinctive features of' G~'ass-J. One is that its focus is on the short units in spontaneous speech, called utter'auce units. An utterance uniL instead of a sentence as in Gral-J is used as a grammatical category and is taken as the start symbol. A Grass-J-based parser takes an utterance unit as input and outputs the representation of the speech act (illoeutionary act) performed by the unit. The other distinctive feature is a focus on expressions peculiar to spontaneous speech, and here we explain how to augment (h'at-J so that it can handle them. Previous studies of spontaneous speech analysis have focused mainly on repairs and ellipses (Bear et el., 1992; l,anger, 1990; Nakatani &amp; Hirschberg, 1993; Otsuka ~; Okada, 1992), rather than expressions peculiar to spontaneous speech.</Paragraph>
    <Paragraph position="7"> This paper first describes Grat-J, and then classities distinctive phenomena in Japanese spontaneous speech. It then describes Grass-Y and presents several analysis examples.</Paragraph>
    <Paragraph position="8">  1. Subcategorization rule Rule for NP (with particle) -VP constructions.</Paragraph>
    <Paragraph position="10"> = (C sere restric) u (H sere restric) Symbols M, C, and tt are not names of categories but variables, or identifiers of root nodes in the graphs representing feature structures. M, C, and H correspond to mother, complement daughter, and head daughter.</Paragraph>
    <Paragraph position="11"> The head daughter's subcat feature value is a set of feature structures.</Paragraph>
  </Section>
class="xml-element"></Paper>