<?xml version="1.0" standalone="yes"?>
<Paper uid="P89-1025">
  <Title>PLANNING TEXT FOR ADVISORY DIALOGUES&amp;quot;</Title>
  <Section position="3" start_page="0" end_page="203" type="intro">
    <SectionTitle>
INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> Providing explanations in an advisory situation is a highly interactive process, requiring a dialogue between advice-giver and advice-seeker (Pollack eta/., 1982). Participating in a dialogue requires the ability to reason about previous responses, e.g., to interpret the user's follow-up questions in the context of the on-going conversation and to determine how to clarify a response when necessary. To provide these capabilities, an explanation facility must understand what it was trying to convey and how that information was conveyed, i.e., the intentional structure behind the explanation, including thegoal of the explanation as a whole, the subgoal(s)of individual parts of the explanation, and the rhetorical means used to achieve them.</Paragraph>
    <Paragraph position="1"> Researchers in natural language under. standing have recognized the need for such information. In their work on discourse analysis, Grosz and Sidner (1986) argue that it is necessary to represent the intentional structure, the attentional structure (knowledge about which aspects of a dialogue are in focus at each point), and the linguistic structure of &amp;quot;The research described in this paper was supported by the Defense Advanced Research Projects Agency (DARPA) under a NASA Ames cooperative agreement number NCC 2-520. The authors would like to thank William Swartout for comments on earlier versions of this paper.</Paragraph>
    <Paragraph position="2">  the discourse. In contrast, most text generation systems (with the notable exception of KAMP (Appelt, 1985)) have used only rhetorical and attentional information to produce coherent text (McKeown, 1985, McCoy, 1985, Paris, 1988b), omitting intentional information, or conflating intentional and rhetorical information (Hovy, 1988b). No text generation system records or reasons about the rhetorical, the attentional, as well as the intentional structures of the texts it produces.</Paragraph>
    <Paragraph position="3"> In this paper, we argue that to successfully participate in an explanation dialogue, a generation system must maintain the kinds of information outlined by Grosz and Sidner as well as an explicit representation of the rhetorical structure of the texts it generates.</Paragraph>
    <Paragraph position="4"> We present a text planner that builds a de- tailed text plan, containing the intentional, attentional, and rhetorical structures of the responses it produces. The main focus of this paper is the plan language and the plan structure built by our system. Examples of how this structure is used in answering follow-up questions appear in (Moore and Swartout, 1989).</Paragraph>
  </Section>
class="xml-element"></Paper>