<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-1045">
  <Title>Pronominalization revisited*</Title>
  <Section position="7" start_page="311" end_page="311" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> This paper has presented a new algorithm tbr the pronominalization of third person discourse entities. The Mgorithm, first, is implemented as a reusable module tbr generation systenls and, second, provides a theoretical account of pronominalization in general.</Paragraph>
    <Paragraph position="1"> The proposed algorithm provides a solution for question \[~ above by widening the definition of local Ibcus to be a set with possibly more than one referent. The Mgorithm also oilers a new solution fbr problem \[~ above, aml)iguous pronoun generation. Discom'se structuring (~\]) is assumed as given. A sufficiently fine-grained discourse structuring has been explored, for example, by McCoy and Strube fbr their donlmn of newspaper articles, but remMns an issue fbr future research fbr other domains. We have shown that next to 1)roxilnity, the discourse status of the mltecedcnt is a main criterion for triggering pronomilmlization.</Paragraph>
    <Paragraph position="2"> The suggested algorithm generalizes known fbcusing accounts. Gundel et al. (1993)'s cognitive slat, us of being &amp;quot;in fbcus&amp;quot; is now approximated by the set of all discourse-old entities and the subject of the previous utterance. The new focus determination is also a generalization of centering's Cb. The focus so defined serves two functions simultaneously: to trigger 1)ronominMization, and to provide the set; of competitors for pronoun generation in ambiguous contexts.</Paragraph>
    <Paragraph position="3"> Although our training corpus is too small to justify general clMms, the ewduation with respect to tile newspaper genre provides evidence that this finding is valid for planned discourse ill generM, independent of the concrete genre.</Paragraph>
  </Section>
class="xml-element"></Paper>