<?xml version="1.0" standalone="yes"?>
<Paper uid="P86-1033">
  <Title>LINGUISTIC COHERENCE: A PLAN-BASED ALTERNATIVE</Title>
  <Section position="2" start_page="0" end_page="215" type="intro">
    <SectionTitle>
INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> In order to interpret a sequence of utterances fully, one must know how the utterances cohere; that is, one must be able to infer implicit relationships as well as non-relationships between the utterances. Consider the following fragment, taken from a terminal transcript between a user and a computer operator (Mann \[12\]): Could you mount a magtape for me? It's tape 1.</Paragraph>
    <Paragraph position="1"> Such a fragment appears coherent because it is easy to infer how the second utterance is related to the first. Contrast this with the following fragment: Could you mount a magtape for me? It's snowing like crazy.</Paragraph>
    <Paragraph position="2"> This sequence appears much less coherent since now there is no obvious connection between the two utterances. While one could postulate some connection (e.g., the speaker's magtape contains a database of places to go skiing), more likely one would say that there is no relationship between the utterances. Furth-IThis work was done at the Department of Computer Science. University of Rochester. Rochester NY 14627. and supported in part by DARPA under Grant N00014-82-K-0193. NSF under Grant DCR8351665. and ONR under Grant N0014-80-C-0197. ermore, because the second utterance violates an expectation of discourse coherence (Reichman \[16\].</Paragraph>
    <Paragraph position="3"> Hobbs \[8\], Grosz, Joshi, and Weinstein \[6\]), the utterance seems inappropriate since there are no linguistic clues (for example, prefacing the utterance with &amp;quot;incidentally&amp;quot;) marking it as a topic change. The identification and specification of sets of linguistic relationships between utterances 2 forms the basis for many computational models of discourse (Reichman \[17\], McKeown \[14\], Mann \[13\], Hobbs \[8\], Cohen \[3\]). By limiting the relationships allowed in a system and the ways in which relationships coherently interact, efficient mechanisms for understanding and generating well organized discourse can be developed.</Paragraph>
    <Paragraph position="4"> Furthermore, the approach provides a framework for explaining the use of surface linguistic phenomena such as clue words, words like &amp;quot;incidentally&amp;quot; that often correspond to particular relationships between utterances. Unfortunately. while these theories propose relationships that seem intuitive (e.g. &amp;quot;elaboration,&amp;quot; as might be used in the first fragment above), there has been little agreement on what the set of possible relationships should be, or even if such a set can be defined. Furthermore, since the formalization of the relationships has proven to be an extremely difficult task, such theories typically have to depend on unrealistic computational processes. For example.</Paragraph>
    <Paragraph position="5"> Cohen \[3\] uses an oracle to recognize her &amp;quot;evidence&amp;quot; relationships. Reichman's \[17\] use of a set of conversational moves depends on the future development of extremely sophisticated semantics modules. Hobbs \[8\] acknowledges that his theory of coherence relations &amp;quot;may seem to be appealing to magic,&amp;quot; since there are several places where he appeals to as yet incomplete subtheories. Finally, Mann \[13\] notes that his theory of rhetorical predicates is currently descriptive rather than constructive. McKeown's \[14\] implemented system of rhetorical predicates is a notable exception, but since her predicates have associated semantics expressed in terms of a specific data base system the approach is not particularly general.</Paragraph>
    <Paragraph position="6"> -'Although in some theories relationships hold between group of utterances, in others between clauses of an utterance, these distinctions will not be crucial for the purposes of this paper.  This paper presents a new model for representing and recognizing implicit relationships between utterances. Underlying linguistic relationships are formulated as discourse plans in a plan-based theory of dialogue understanding. This allows the specification and formalization of the relationships within a computational framework, and enables a plan recognition algorithm to provide the link from the processing of actual input to the recognition of underlying discourse plans. Moreover, once a plan recognition system incorporates knowledge of linguistic relationships, it can then use the correlations between linguistic relationships and surface linguistic phenomena to guide its processing. By incorporating domain independent linguistic results into a plan recognition framework, a formalization and computability generally not available in the earlier works is provided.</Paragraph>
    <Paragraph position="7"> The next section illustrates the discourse plan representation of domain independent knowledge about communication as knowledge about the planning process itself. A plan recognition process is then developed to recognize such plans, using linguistic clues, coherence preferences, and constraint satisfaction. Finally, a detailed example of the processing of a dialogue fragment is presented, illustrating the recognition of various types of relationships between utterances.</Paragraph>
  </Section>
class="xml-element"></Paper>