<?xml version="1.0" standalone="yes"?>
<Paper uid="P98-1090">
  <Title>Long Distance Pronominalisation and Global Focus</Title>
  <Section position="10" start_page="555" end_page="555" type="concl">
    <SectionTitle>
6 Conclusions
</SectionTitle>
    <Paragraph position="0"> Our main intent in looking at long-distance pronominalisation was to make some of the aspects of the G&amp;S model of attentional state more precise, and to clarify its connection with earlier work by Sidner. The evidence we have presented suggests a main conclusion and a corollary. The main conclusion is that the uses of long-distance pronouns in our corpus can be explained as cases of reference to the MSE of a segment whose associated focus space is still on the stack. The corollary is that these examples can be accounted for within a G&amp;S-style model of discourse structure, provided that the theory is augmented by singling out some entities in focus spaces, and having these entities do some of the work done by Sidner's stack of discourse foci.</Paragraph>
    <Paragraph position="1"> A concern with studies of this type is that notions such as 'most salient entity' are hard to define, and it's not obvious that two different researchers would necessarily agree on what is the MSE of a given sentence. Work on verifying whether the notion we are assuming can indeed be reliably identified is under way as part of the GNOME project.</Paragraph>
  </Section>
class="xml-element"></Paper>