<?xml version="1.0" standalone="yes"?>
<Paper uid="P91-1005">
  <Title>AN ALGORITHM FOR PLAN RECOGNITION IN COLLABORATIVE DISCOURSE*</Title>
  <Section position="3" start_page="0" end_page="0" type="intro">
    <SectionTitle>
INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> To make sense of each other's utterances, conversational participants must recognize the intentions behind those utterances. Thus, a model of intended plan recognition is an important component of a theory of discourse understanding. The model must distinguish each agent's beliefs and intentions from the other's and avoid assumptions about the correctness or completeness of the agents' beliefs.</Paragraph>
    <Paragraph position="1"> Early work on plan recognition in discourse, e.g.</Paragraph>
    <Paragraph position="2"> Allen &amp; Perrault (1980); Sidner &amp; Israel (1981), was based on work in AI planning systems, in particular the STRIPS formalism (Fikes and Nilsson, 1971). However, as Pollack (1986) has argued, because these systems do not differentiate between the beliefs and intentions of the different conversational participants, they are insufficient for modelling discourse. Although Pollack proposes a model that does make this distinction, her model has other shortcomings. In particular, it assumes a master/slave relationship between agents (Grosz and Sidner, 1990) and that the inferring agent has complete and accurate knowledge of domain actions. In addition, like many earlier systems, it relies upon a set of heuristics to control the application of plan inference rules.</Paragraph>
    <Paragraph position="3"> In contrast, Kautz (1987; 1990) presented a theoretical formalization of the plan recognition problem, *This research has been supported by U S WEST Advanced Technologies and by a Bellcore Graduate Fellowship. null and a corresponding algorithm, in which the only conclusions that are drawn are those that are &amp;quot;absolutely justified.&amp;quot; Although Kautz's work is quite elegant, it too has several deficiencies as a model of plan recognition for discourse. In particular, it is a model of keyhole recognition m the inferring agent observes the actions of another agent without that second agent's knowledge -- rather than a model of intended recognition.</Paragraph>
    <Paragraph position="4"> Furthermore, both the inferring and performing agents are assumed to have complete and correct knowledge of the domain.</Paragraph>
    <Paragraph position="5"> In this paper, we present an algorithm for intended recognition that is based on the SharedPlan model of collaboration (Grosz and Sidner, 1990; Lochbaum et al., 1990) and that, as a result, overcomes the limitations of these previous models. We begin by briefly presenting the action representation used by the algorithm and then discussing the type of plan recognition necessary for the construction of a SharedPlan. Next, we present the algorithm itself, and discuss an initial implementation. Finally, because Kautz's plan recognition Mgorithms are not necessarily tied to the assumptions made by his formal model, we directly compare our algorithm to his.</Paragraph>
  </Section>
class="xml-element"></Paper>