<?xml version="1.0" standalone="yes"?>
<Paper uid="P96-1039">
  <Title>An Information Structural Approach to Spoken Language Generation</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> While research on generating coherent written text has flourished within the computational linguistics and artificial intelligence communities, research on the generation of spoken language, and particularly intonation, has received somewhat less attention.</Paragraph>
    <Paragraph position="1"> In this paper, we argue that commonly employed models of text organization, such as schemata and rhetorical structure theory (RST), do not adequately address many of the issues involved in generating spoken language. Such approaches fail to consider contextually bound focal distinctions that are manifest through a variety of different linguistic and paralinguistic devices, depending on the language.</Paragraph>
    <Paragraph position="2"> In order to account for such distinctions of focus, we employ a two-tiered information structure representation as a framework for maintaining local coherence in the generation of natural language.</Paragraph>
    <Paragraph position="3"> The higher tier, which delineates the lheme, that which links the utterance to prior utterances, and the theme, that which forms the core contribution of the utterance to the discourse, is instrumental in determining the high-level organization of information within a discourse segment. Dividing semantic representations into their thematic and rhematic parts allows propositions to be presented in a way that maximizes the shared material between utterances.</Paragraph>
    <Paragraph position="4"> The lower tier in the information structure representation specifies the semantic material that is in &amp;quot;focus&amp;quot; within themes and themes. Material may be in focus for a variety of reasons, such as to emphasize its &amp;quot;new&amp;quot; status in the discourse, or to contrast it with other salient material. Such focal distinctions may affect the linguistic presentation of information. For example, the it-cleft in (1) may mark John as standing in contrast to some other recently mentioned person. Similarly, in (2), the pitch accent on red may mark the referenced car as standing in contrast to some other car inferable from the discourse context 3  (1) It was John who spoke first.</Paragraph>
    <Paragraph position="5"> (2) Q: Which car did Mary drive?  A: (MARY drove)th (the RED car.)rh L+H* LH(%) H* LL$ By appealing to the notion that the simple rise-fall tune (H* LL%) very often accompanies the rhematic material in an utterance and the rise-fall-rise tune often accompanies the thematic material (Steedman, 1991 i Prevost and Steedman, 1994), we present a spoken language generation architecture for producing short spoken monologues with contextually appropriate intonation.</Paragraph>
  </Section>
class="xml-element"></Paper>