<?xml version="1.0" standalone="yes"?>
<Paper uid="P86-1033">
  <Title>LINGUISTIC COHERENCE: A PLAN-BASED ALTERNATIVE</Title>
  <Section position="6" start_page="221" end_page="221" type="concl">
    <SectionTitle>
CONCLUSIONS
</SectionTitle>
    <Paragraph position="0"> This paper has presented a framework for both representing as well as recognizing relationships between utterances. The framework, based on the assumption that people's utterances reflect underlying plans, reformulates the complex inferential processes relating utterances within a plan-based theory of dialogue understanding. A set of meta-plans called discourse plans were introduced to explicitly formalize utterance relationships in terms of a small set of underlying plan manipulations. Unlike previous models of coherence, the representation was accompanied by a fully specified model of computation based on a process of plan recognition. Constraint satisfaction is used to coordinate the recognition of discourse plans, domain plans, and their relationships.</Paragraph>
    <Paragraph position="1"> Linguistic phenomena associated with coherence relationships are used to guide the discourse plan recognition process.</Paragraph>
    <Paragraph position="2"> Although not the focus of this paper, the incorporation of topic relationships into a plan-based framework can also be seen as an extension of work in plan recognition. For example, Sidner \[21,24\] analyzed debuggings (as in the dialogue above) in terms of multiple plans underlying a single utterance.</Paragraph>
    <Paragraph position="3"> As discussed fully in Litman and Allen \[11\], the representation and recognition of discourse plans is a systemization and generalization of this approach.</Paragraph>
    <Paragraph position="4"> Use of even a small set of discourse plans enables the principled understanding of previously problematic classes of dialogues in several task-oriented domains.</Paragraph>
    <Paragraph position="5"> Ultimately the generality of any plan-based approach depends on the ability to represent any domain of discourse in terms of a set of underlying plans.</Paragraph>
    <Paragraph position="6"> Recent work by Grosz and Sidner \[7\] argues for the validity of this assumption.</Paragraph>
  </Section>
class="xml-element"></Paper>