<?xml version="1.0" standalone="yes"?>
<Paper uid="J86-3001">
  <Title>ATTENTION, INTENTIONS, AND THE STRUCTURE OF DISCOURSE</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> This paper presents the basic elements of a computational theory of discourse structure that simpfifies and expands upon previous work. By specifying the basic units a discourse comprises and the ways in which they can relate, a proper account of discourse structure provides the basis for an account of discourse meaning.</Paragraph>
    <Paragraph position="1"> An account of discourse structure also plays a central role in language processing because it stipulates constraints on those portions of a discourse to which any given utterance in the discourse must be related.</Paragraph>
    <Paragraph position="2"> An account of discourse structure is closely related to two questions: What individuates a discourse? What makes it coherent? That is, faced with a sequence of utterances, how does one know whether they constitute a single discourse, several (perhaps interleaved) discourses, or none? As we develop it, the theory of discourse structure will be seen to be intimately connected with two nonlinguistic notions: intention and attention. Attention is an essential factor in explicating the processing of utterances in discourse. Intentions play a primary role in explaining discourse structure, defining discourse coherence, and providing a coherent conceptualization of the term &amp;quot;discourse&amp;quot; itself.</Paragraph>
    <Paragraph position="3"> Copyright 1986 by the Association for Computational Linguistics. Permission to copy without fee all or part of this material is granted provided that the copies are not made for direct commercial advantage and the CL reference and this copyright notice are included on the first page. To copy otherwise, or to republish, requires a fee and/or specific permission. 0362-613X/86/030175-204503.00 Computational Linguistics, Volume 12, Number 3, ~luly-September 1986 175 Barbara J. Grosz and Candace L. Sidner Attention, Intentions, and the Structure of Discourse The theory is a further development and integration of two lines of research: work on focusing in discourse (Grosz 1978a, 1978b, 1981) and more recent work on intention recognition in discourse (Sidner and Israel 1981; Sidner 1983; 1985; Allen 1983, Litman 1985; Pollack 1986). Our goal has been to generalize these constructs properly to a wide range of discourse types.</Paragraph>
    <Paragraph position="4"> Grosz (1978a) demonstrated that the notions of focusing and task structure are necessary for understanding and producing task-oriented dialogue. One of the main generalizations of previous work will be to show that discourses are generally in some sense &amp;quot;task-oriented,&amp;quot; but the kinds of &amp;quot;tasks&amp;quot; that can be engaged in are quite varied - some are physical, some mental, others linguistic. Consequently, the term &amp;quot;task&amp;quot; is misleading; we therefore will use the more general terminology of intentions (e.g., when speaking of discourse purposes) for most of what we say.</Paragraph>
    <Paragraph position="5"> Our main thesis is that the structure of any discourse is a composite of three distinct but interacting components: * the structure of the actual sequence of utterances in the discourse; * a structure of intentions; * an attentional state.</Paragraph>
    <Paragraph position="6"> The distinction among these components is essential to an explanation of interruptions (see Section 5), as well as to explanations of the use of certain types of referring expressions (see Section 4.2) and various other expressions that affect discourse segmentation and structure (see Section 6). Most related work on discourse structure (including Reichman-Adar 1984, Linde 1979, Linde and Goguen 1978, Cohen 1983) fails to distinguish among some (or, in some cases, all) of these components. As a result, significant generalizations are lost, and the computational mechanisms proposed are more complex than necessary. By carefully distinguishing these components, we are able to account for significant observations in this related work while simplifying both the explanations given and computational mechanisms used.</Paragraph>
    <Paragraph position="7"> In addition to explicating these linguistic phenomena, the theory provides an overall framework within which to answer questions about the relevance of various segments of discourse to one another and to the overall purposes of the discourse participants. Various properties of the intentional component have implications for research in natural-language processing in general. In particular, the intentions that underlie discourse are so diverse that approaches to discourse coherence based on selecting discourse relationships from a fixed set of alternative rhetorical patterns (e.g., Hobbs 1979, Mann and Thompson 1983, Reichman 1981) are unlikely to suffice.</Paragraph>
    <Paragraph position="8"> The intentional structure introduced in this paper depends instead on a small number of structural relations that can hold between intentions. This study also reveals several problems that must be confronted in expanding speech-act-related theories (e.g., Allen and Perrault 1980, Cohen and Levesque 1980, Allen 1983) from coverage of individual utterances to coverage of extended sequences of utterances in discourse.</Paragraph>
    <Paragraph position="9"> Although a definition of discourse must await further development of the theory presented in this paper, some properties of the phenomena we want to explain must be specified now. In particular, we take a discourse to be a piece of language behavior that typically involves multiple utterances and multiple participants. A discourse may be produced by one or more of these participants as speakers or writers; the audience may comprise one or more of the participants as hearers or readers. Because in multi-party conversations more than one participant may speak (or write) different utterances within a segment, the terms speaker and hearer do not differentiate the unique roles that the participants maintain in a segment of a conversation. We will therefore use the terms initiating conversational participant (ICP) and other conversational participant(s) (OCP) to distinguish the initiator of a discourse segment from its other participants.</Paragraph>
    <Paragraph position="10"> The ICP speaks (or writes) the first utterance of a segment, but an OCP may be the speaker of some subsequent utterances. By speaking of ICPs and OCPs, we can highlight the purposive aspect of discourse. We will use the terms speaker and hearer only when the particular speaking/hearing activity is important for the point being made.</Paragraph>
    <Paragraph position="11"> In most of this paper, we will be concerned with developing an abstract model of discourse structure; in particular, the definitions of the components will abstract away from the details of the discourse participants.</Paragraph>
    <Paragraph position="12"> Whether one constructs a computer system that can participate in a discourse (i.e., one that is a language user) or defines a psychological theory of language use, the task will require the appropriate projection of this abstract model onto properties of a language user, and specification of additional details (e.g., specifying memory for linguistic structure, means for encoding attentional state, and appropriate representations of intentional structure). We do, however, address ourselves directly to certain processing issues that are essential to the computational validity of the \[abstract\] model and to its utilization for a language-processing system or psychological theory.</Paragraph>
    <Paragraph position="13"> Finally, it is important to note that although discourse meaning is a significant, unsolved problem, we will not address it in this paper. An adequate theory of discourse meaning needs to rest at least partially on an adequate theory of discourse structure. Our concern is with providing the latter.</Paragraph>
    <Paragraph position="14"> The next section examines the basic theory of discourse structure and presents an overview of each of the components of discourse structure. Section 3 analyzes two sample discourses - a written text and a fragment of task-oriented dialogue - from the perspective of the theory being developed; these two examples are also used to illustrate various points in the remainder of the paper. Section 4 investigates various processing 176 Computational Linguistics, Volume 12, Number 3, July-September 1986 Barbara J. Grosz and Candace L. Sidner Attention, Intentions, and the Structure of Discourse issues that the theory raises. The following two sections describe the role of the discourse structure components in explaining various properties of discourse, thereby corroborating the necessity of distinguishing among its three components. Section 7 describes the generalization from utterance-level to discourse-level intentions, establishes certain properties of the latter, and contrasts them with the rhetorical relations of alternative theories.</Paragraph>
    <Paragraph position="15"> Finally, Section 8 poses a number of outstanding research questions suggested by the theory.</Paragraph>
  </Section>
class="xml-element"></Paper>