<?xml version="1.0" standalone="yes"?>
<Paper uid="C94-1051">
  <Title>Anticipating the Reader's Problems and the Automatic Generation of Paraphrases</Title>
  <Section position="4" start_page="0" end_page="0" type="intro">
    <SectionTitle>
2. OTHER NOTIONS OF &amp;quot;PARAPIIRASE&amp;quot;
</SectionTitle>
    <Paragraph position="0"> Notions of &amp;quot;paraphrase&amp;quot; exist which differ fiom the one presented above. In linguistics, especially Trimslbnnationat Grammar, cf. e.g. (Smaby 1971), (Nolml 1970), the paraphrase relation is induced by the rules of the limguage system. Two formulations count as paraphrases of each other if they can be derived from a common deep structure, e.g. the active and the passive version of a sentence. So, the paraphrase relation is completely independent of the situation and communication participants. This view has been heavily criticiscd, cf.</Paragraph>
    <Paragraph position="1"> (Ungeheuer 1969).</Paragraph>
    <Paragraph position="2"> In CI,, the generation of a surface form from a meaning representation is sometimes called paraphrase generation, especially if different surface forms can Ix: generated for the same meaning representation. An ,'unbiguity exists here, because the paraphrase relation can be meant to hold (a) between the mcaning representation and the NL text derived from it or (b) between two alternative formulations which could both be derived from the meaning representation.</Paragraph>
    <Paragraph position="3"> 1 will shnply call case a) &amp;quot;generation&amp;quot; because that is what it means: deriving a text from an underlying meaning representalion. Case b), exemplified by (Gokhn~m 1975) and most wolk in the area of Meaning-Text Models, cf. e.g. (lordanskaja, Kittredge &amp; Polgut3re 1991), (Mercuk 1981), stresses the possibility of an alternative formulation which could be uttered instead of another formulation, whereas in seclion 1 we talked of paraphrasing as uttering a formulation in a&amp;lition to imother formulation. To differentiate between these cases I will not call case b) tutraphrase but - in accord:race with classical rhetoric - periphrase.</Paragraph>
  </Section>
class="xml-element"></Paper>