<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-1045">
  <Title>Pronominalization revisited*</Title>
  <Section position="2" start_page="0" end_page="0" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Besides the well established problem of ln'onoun resolution, pronoun generation is now attracting renewed attention. In the past, generation systelns generated pronouns without attaching much importance to the problem, one notable exception being the classical algorithm of Dale (1990), loosely based on centering theory. With the emergence of corpus based studies in comtmrational linguistics, the question arises whether it is possible to refine known standard algorithms, or whether an improvement is only to be achieved with the hell) of world knowledge reasoning - a matter too complex to be dealt with reliably at this time. Tile Ibrlner direction is represented by tile pioneering work of McCoy and Strube (1999). They propose a refined algorithm for tile choice between definite description on the one hand and pronoun on the other for * The work reported in this paper has been calmed out with the tinancial support of UK ESPllC grant L51126.</Paragraph>
    <Paragraph position="1"> animate referents I , which is based on distancG time structure mid ambiguity constraints.</Paragraph>
    <Paragraph position="2"> Here we introduce a more general algoritlnn for the pronominalization decision that is valid not only for animate but for inanimate referents as well. In conformity with McCoy and Strube, we group noun phrases with definite determiner and proper nalnes together under tile term &amp;quot;det'inite description&amp;quot;. The algorithm proposes a new pronominalization strategy, which beyond McCoy and Strube (1999)'s criteria makes use of the discom'se status of the antecedent and parallelism effects.</Paragraph>
    <Paragraph position="3"> The algorithm has been implemented as the reusable module gnome-np. It has been re-used in tile web hypertext generation system ILEX (see Oberlander el; al. (1998)). It shows ml accuracy over 87% with respect to two corpora (each 5000 words) of difl'erent genres.</Paragraph>
  </Section>
class="xml-element"></Paper>