<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-1056">
  <Title>ABSTRACT GENERATION BASED ON RHETORICAL STRUCTURE EXTRACTION</Title>
  <Section position="3" start_page="0" end_page="344" type="intro">
    <SectionTitle>
2 INTRODUCTION
</SectionTitle>
    <Paragraph position="0"> Abstract generation is, like Machine Translation, one of the ultimate goal of Natural Language Processing. IIowever, since conventional word-frequency-based abstract generation systems(e.g. \[Kuhn 58\]) are lacking in inter-sentential or discourse-structural analysis, they are liable to generate incoherent abstracts. On the other hand, conventional knowledge or script-based abstract generation systems(e.g.</Paragraph>
    <Paragraph position="1"> \[behnert 801, \[Fum 86\]), owe their success to the li,nitation of the domain, and cannot be applied to document with varied subjects, such ,as popular scientific magazine. To realize a domain-independent abstract generation system, a computational theory for analyzing linguistic discourse structure and its practical procedure must be established.</Paragraph>
    <Paragraph position="2"> ltobbs developed a theory in which lie arranged three kinds of relationships between sentences from the text coherency viewpoint \[Hobbs 79\].</Paragraph>
    <Paragraph position="3"> Grosz and Sidner proposed a theory which accounted for interactions between three notions on discourse: linguistic structure, intention, and attention \[C, rosz et al. 86\].</Paragraph>
    <Paragraph position="4"> l,itman and Allen described a model in which a discourse structure of conversation was built by recognizing a participanUs plans \[Litman et al. 87\].</Paragraph>
    <Paragraph position="5"> 'l'hese theories all depend on extra-linguistic knowledge, the accumulation of which presents a problem in the realization of a practical analyzer.</Paragraph>
    <Paragraph position="6"> Cohen proposed a framework for analyzing the structure of argumentative discourse \[Cohen 87\], yet did not provkle a concrete identification procedure for 'evidence' relationships between sentences, where no linguistic clues indicate the relationships. Also, since only relationships between successive sentences were considered, the scope which the relationships cover cannot be analyzed, even if explicit connectives are detected.</Paragraph>
    <Paragraph position="7"> Mama and Thompson proposed a linguistic structure of text describing relationships between sentences and their relative importance \[Mann et al. 87\]. llowever, no method for extracting the relationships from superficial linguistic expressions was described in their paper.</Paragraph>
    <Paragraph position="8"> We have developed a computational rnodel of discourse for Japanese expository writings, and implemented a practical procedure for extracting discourse structure\[Sumita 92\]. In our model, discourse structure is deiined ,as the rhetorical structure, i.e., the compound of rhetorical relations between sentences in text. Abstr~t generation is realized ~s a suitaMe application of the extracted rhetorical structure. In this paper we describe briefly our discourse model and discuss the abstract generation system based on it.</Paragraph>
  </Section>
class="xml-element"></Paper>