<?xml version="1.0" standalone="yes"?>
<Paper uid="W00-1411">
  <Title>An integrated framework for text planning and pronominalisation</Title>
  <Section position="2" start_page="0" end_page="77" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"/>
    <Section position="1" start_page="0" end_page="0" type="sub_section">
      <SectionTitle>
1.1 Issues in pronoun generation
</SectionTitle>
      <Paragraph position="0"> The appropriate realisation of anaphoric expressions is a long-standing problem in NLG research. However, as McCoy and Strube (1999) observe, few researchers have developed sophisticated algorithms for pronoun generation. A typical approach, exemplified by Dale (1993), Reiter and Dale (1997) is to pronominalise some distinguished referent which was mentioned in the previous sentence according to a domain-dependent criterion of prominence or salience. McCoy and Strube (op cir.) offer a more complex algorithm based on the notion of &amp;quot;discourse threads&amp;quot;, for which they report an accuracy of 85% when tested against a corpus of naturally-occurring texts. Their approach makes some fundamental assumptions about discourse structure which appear to be beyond the capabilities of current text and sentence planners and are incompatible with the widelyaccepted notion of discourse structure as a tree with non-crossing branches (e.g., Mann and Thompson 1987).</Paragraph>
      <Paragraph position="1"> We argue for an approach which integrates the tasks of text planning and choice of referring expression on the following grounds: o portability: this approach should be compatible with any system that employs hierarchical text planning and certain basic grammatical categories; o coherence: we claim that text planning needs to be driven in part by the goal of maintaining referential continuity: obtaining a favourable ordering of clauses, and of arguments within clauses, is likely to increase opportunities for non-ambiguous pronoun use.</Paragraph>
      <Paragraph position="2"> The latter claim is not new, but underlies the Centering Theory (CT) of Grosz, Joshi and Weinstein (1995, hereafter &amp;quot;GJW&amp;quot;).</Paragraph>
    </Section>
    <Section position="2" start_page="0" end_page="77" type="sub_section">
      <SectionTitle>
1.2 Issues in Text Planning
</SectionTitle>
      <Paragraph position="0"> Text Planning is one of the distinct tasks identified in Reiter's &amp;quot;consensus&amp;quot; architecture for Natural Language Generation (Reiter 1994, Reiter and Dale 1997): Text Planning- deciding the content of a message, and organising the component propositions into a text tree; Sentence Planning - aggregating propositions into clausal units and choosing lexical items corresponding to concepts in the knowledge base; Linguistic realisation - surface details Such as agreement, orthography etc.</Paragraph>
      <Paragraph position="1"> Following Scott and de Souza (1990), we assume that the component propositions to be realised in a text are organised in a tree structure  in which ternfinal nodes are elementary propositions and non-terminal nodes represent discourse relations as .detined by e~g:,. Rhetorical Structure Theory (RST, Mann and Thompson 1987). This structure only partially constrains the linear order in which the propositions will be realised -- in other words, any RST structure specifies a range of possible text plans. We propose as an additional constraint that the generator should seek to maximise continuity of reference as determined by centering theory, and we argue that- this enables us to select the most cohesive variants from a set of text plans. The RST tree itself is produced by an interactive knowledge base editor which allows a user to control both semantic content and rhetorical structure via a sequence of choices guided by a natural language interface.</Paragraph>
    </Section>
  </Section>
class="xml-element"></Paper>