<?xml version="1.0" standalone="yes"?>
<Paper uid="P88-1016">
  <Title>A COMPUTATIONAL THEORY OF PERSPECTIVE AND REFERENCE IN NARRATIVE</Title>
  <Section position="5" start_page="136" end_page="136" type="concl">
    <SectionTitle>
7. CONCLUSIONS AND FUTURE RESEARCH. Many
</SectionTitle>
    <Paragraph position="0"> problems remain to be solved. Our discourse process cannot recognize subjective contexts that are not established by the linguistic signals it relies on, and general principles are needed to explain how readers recognize the ending boundaries of subjective contexts. We are investigating how tense, deictic terms (cf. Bruder et aL (1986), Bantield (1982)), the characters' goals (cf. Wilansky (1983)), and the argumant structure (of. Cohen (1987)) often exhibited by thoughts might be used to recognize the boundaries of subjectlve contexts. Branches 2 and 3 of algorithm (A1) need to be expanded to determine who the subjective character is if the actor focus isn't a reasonable candidate and no paranthetical appea~. We are investigating how focus of attention (cf. Grosz (1981), Sidner (1983)) can be incorporated into algorithm (A2) in such a way that anaphoric references reflecting the beliefs of a character can be understood. Finally, there is the general problem of revision. Our algorithms assume that signals occur at the beginning of subjective contexts. However, there are cases when a subjective context cannot be recognized until some of it has already been parsed. A difficult case is inustrated by the following: &amp;quot;CaJody was rich and famous, c2why wasn't she happy? Bin wondered.&amp;quot; Only after reading (C2) can the reader recognize that (C1) is a represented thought.</Paragraph>
    <Paragraph position="1"> We have erguad that a discourse-level approach must be taken to the problem of recognizing character's thoughts and perceptions in third-person narrative. Our discourse process, which is implemented in an ATN grammar interfaced to SNePS, recognizes subjective contexts that are linguistically signaled in ways frequantly employed in naturally-occurring narratives. By using the results of the discourse process to determine the belief context needed m onderstand refermces, our reference algorithm demonstrates how perspective affects referance in third-person narrative.</Paragraph>
    <Paragraph position="2"> 8, ACKNOWLEDGMENTS. We are indebted to Mary Galbraith, David Zubin, Sandra Peters, Stuart Shapiro, and the other members of the SUNY Buffalo Graduate Group in Cognitive Science and the SNePS Research Group for many discussions end ideas. This research was supported in part by NSF grauts IST-8504713, IRI-8610517.</Paragraph>
  </Section>
class="xml-element"></Paper>