File Information

File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/concl/00/w00-1411_concl.xml

Size: 1,865 bytes

Last Modified: 2025-10-06 13:52:56

<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-1411">
  <Title>An integrated framework for text planning and pronominalisation</Title>
  <Section position="7" start_page="83" end_page="83" type="concl">
    <SectionTitle>
4 Conclusion
</SectionTitle>
    <Paragraph position="0"> This paper has highlighted some implications of Centering Theory for planning coherent text.</Paragraph>
    <Paragraph position="1"> We show that by making some assumptions about which entities are potential Cps, we can determine Cbs, Cps, and hence transitions, in the text planning stage. This allows the text planner to select the proposition sequence that yields the best continuity of reference, or to balance the goal of referential continuity against other factors. For instance, there may be a preference for Satellite to follow Nucleus for some discourse relations, even if this results in a greater number of defects according to centering considerations. There are difficulties in evaluating algorithms for specific tasks which are embedded in a generation system, since the quality of the output is limited by the functionalities of the system as a whole. In particular, the task of generating appropriate referring expressions cannot be tackled in isolation from other tasks which contribute to the coherence of a text.</Paragraph>
    <Paragraph position="2"> The implementation of Centering reported here is a special case of text planning by constraint satisfaction, where the user has control over the different constraints, and this approach means that different strategies for e.g. clause ordering and pronominalisation can easily be compared by inspecting the resulting texts. The evaluation metrics we have presented here are provisional and are a matter for further detailed research, which our approach to text generation will facilitate.</Paragraph>
  </Section>
class="xml-element"></Paper>
Download Original XML