<?xml version="1.0" standalone="yes"?>
<Paper uid="W99-0108">
  <Title>Q @ @ @ O O O @ @ O @ O O @ @ 0 @ @ O @ O @ O O O @ @ @ O @ O O @ @ O O @ @ O @ O O O O Generating Anaphoric Expressions: Pronoun or Definite Description?</Title>
  <Section position="4" start_page="63" end_page="64" type="intro">
    <SectionTitle>
2 Previous Work on Pronoun Generation
</SectionTitle>
    <Paragraph position="0"> Few researchers have given serious consideration to the problem of pronoun generation. The most common factot considered has been the accessibility of the refereaL If the referent is sufficiently prominent in the ceding text, a pronoun is usecL Some early generation work (e.g., McDonald (1980), McKeown (1983), McKeown (1985), Appelt (1981)) used a simple mleto implement this idea based on focus (Sidner, 1979) that roughly stated that if the current sentence is about the same thing that the previous sentence was about, use a pronoun to refer to that thing. As was pointed out above, this rule does not provide a very good match with the referring expressions in our corpus.</Paragraph>
    <Paragraph position="1"> Dale (1992)also ~ the generation of pronouns in the context of work on generating referring expressions (Appelt' 1985; Reiter, 1990). Dale specified an algorithm that essentially generated the smallest refen'ing expression that distinguished the object in question from</Paragraph>
    <Paragraph position="3"> * nil others in the context) He generated a pronoun (or ellipsis) if one were adequate and if the object being referred to was the center of the last utterance (where the notion of center was defined in a domain dependent fashion). As an example of the kinds of texts he generated consider: &amp;quot;Soak the butterbeaus. Drain and rinse them.&amp;quot; Such an account of pronoun generation, based on center constancy, appears to work quite well in the domain Dale considered. However, as pointed out in Example 1, it does not seem to explain the patterns found in the texts we analyzed.</Paragraph>
    <Paragraph position="4"> The centering model (Orosz et al., 1995) itself makes predictions about pronoun generation only in a specific instance - that where Rule 1 is appficeble. Centering's Rule 1 states that if any element of the previous utterance's forward looking center list is realized in the current utterance as a pronoun, then the backward looking center must be realized as a pronoun as well (Grosz et al., 1995. p.214). Notice that the Mr. Curtis at the beginning of the second sentence in Example I is an apparent violation of this rule. But, more generally, we must have a theory that is able to handle all cases of pronoun use.</Paragraph>
    <Paragraph position="5"> A pronoun interpretation algorithm based on centering which relied on centering transition preferences was developed in Brennan et aL (1987)~ Using transition preferences in a pronoun generation rule would cover more cases of pronoun use than is covered by Rule 1, but the application of such transition preferences also proved unhelpful in explaining pronoun patterns in our corpus.</Paragraph>
    <Paragraph position="6"> Reichman (1985) and Grosz &amp; Sidner (1986) indicate that discourse segmentation has an effect on the linguistic realization of referring expressions. While this is intuitively appealing, it is unclear how to apply this to the generation problem (in part because it is unclear how to define discourse segments to a generation system). Passonneau (1996) argues for the use of the principles of information adequacy and economy. Her algorithm takes discourse segmentation into account through the use of focus spaces which are associated with discourse segments. Thus, Passonneau explains that a fuller description might be used at a boundary bec__~_use the set of accesu'ble objects changes at discourse segment boundaries (though she combines this consideration with centering theory which may override the decisions due to segment boundaries). While Passonneau's algorithm seems quite appealing, notice that it provides no explanation of how a discourse segment should be defined. The evaluation that she provided used the discourse segments provided by aset of naive subjects who indicated discourse segment boundaries in her texts. Without such boundaries provided, it is impossible to apply her algoritlun. In some sense, the work presented here is consistent with Passonneau's theory..What we attempt to add is a genre-dependent definition of discourse segment (thread) which is well-defined and can be derived from 2This algorithm was later revised in Dale &amp; Reiter (1995) m more adequately reflect human-generated referring expressions and to be more computationally tractable.</Paragraph>
    <Paragraph position="7"> input that any sentence generator must have in order to generate a sentence. On the other hand, we differ from Passonneau in that we do not attempt to make use of focus spaces in generation. Rather we argue for evaluating informational adequacy on the basis of confusable objects near the current sentence in a discourse.</Paragraph>
    <Paragraph position="8"> In the following section we hypothesize that discourse structure in terms of multiple threads does have an effact on appropriate anaphoric expression choice and that the temporal structure of a discourse is a particular instantiation of these threads (in the stories that we have analyzed). We hypothesize that if there is a difference in time between the last reference to an entity and the current reference, a definite description is used (and when the time of the previous and the current reference is the same, a pronoun is used).</Paragraph>
  </Section>
class="xml-element"></Paper>