<?xml version="1.0" standalone="yes"?>
<Paper uid="W96-0417">
  <Title>Strategies for Comparison in Encyclopaedia Descriptions</Title>
  <Section position="7" start_page="168" end_page="169" type="concl">
    <SectionTitle>
5 Conclusions and Future
</SectionTitle>
    <Paragraph position="0"> Work In this paper, we have: described the PEBA-II system, as an example of a system which integrates natural language generation and hypertext in the provision of user-tailored information; null * defined some notions relevant to the study of comparison; and looked at the concept of illustrative comparison in detail, with the aim of defining a mechanism for generating such comparisons that embodies a clear distinction between domain-dependent and domain-independent information.</Paragraph>
    <Paragraph position="1"> For future work, we intend to elaborate upon and extend further the techniques described here. In particular, we intend to make use of these notions in the generation of comparisons which take account of the discourse history; some examples of this phenomenon are discussed in \[Dale and Milosavljevic 1996\].</Paragraph>
  </Section>
class="xml-element"></Paper>