<?xml version="1.0" standalone="yes"?>
<Paper uid="C04-1034">
  <Title>Resolving Individual and Abstract Anaphora in Texts and Dialogues</Title>
  <Section position="2" start_page="0" end_page="1" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> Although most pronominal anaphora resolution algorithms only account for anaphors referring to individual entities, anaphors referring to abstract entities evoked by verbal phrases, clauses or discourse segments (henceforth APAs) are quite common in English see i.a. (Byron and Allen, 1998) and even more in Danish (Navarretta, 2004). Recently, two algorithms for resolving APAs and individual pronominal anaphors (henceforth IPAs) in specific English dialogues have been proposed Eckert and Strube-s (2000) es00 and Byron-s (2002) phora. Furthermore Strube and M&amp;quot;uller (Strube and M&amp;quot;uller, 2003) have presented a machine learning approach for resolving APAs in spoken dialogues.</Paragraph>
    <Paragraph position="1">  Both es00 and phora  We do not discuss this approach further in this paper. null recognise IPAsandAPAs on the basis of semantic constraints on the argument position occupied by the anaphors and account for differences in reference between personal and demonstrative pronouns. In es00 demonstrative pronouns preferentially refer to abstract entities, while personal pronouns preferentially refer to individual ones. es00 resolves IPAs applying Strube-s (1998) algorithm. In phora the antecedents of personal pronouns are searched for looking at their degree of salience which is implemented by word order as in (Grosz et al., 1995). Demonstratives, instead, are searched for in the list of activated entities (Gundel et al., 1993) containing non NP antecedents, which are assumed to be less salient. In phora demonstratives can also refer to Kinds.</Paragraph>
    <Paragraph position="2"> es00 requires that the structure of dialogues has been marked. Byron-s phora-algorithm does not rely on predefined dialogue structure, but only searches for abstract antecedents of APAs in the sentence preceding the anaphor.</Paragraph>
    <Paragraph position="3"> Thus it does not account for APAs referring to larger discourse segments. phora relies on both semantic knowledge and a model of speech acts and accounts for more phenomena than es00.</Paragraph>
    <Paragraph position="4"> Differing from es00, phora has been implemented. null To resolve IPAsandAPAsinDanishtexts and dialogues Navarretta (2004) has proposed the so-called dar-algorithm (Navarretta, 2004). In dar APAs are resolved following the es00 strategy, but dar accounts for the Danish abstract anaphors which occur in much more contexts than the English ones. Individual anaphors are resolved in dar following a novel strategy which combines models which identify high degree of salience with high degree of givenness (topicality) of entities in the hearer-s cognitive model, e.g. (Grosz et al., 1995), with HajiVcov'a et al.-s (1990) salience account which assigns the highest degree of salience to entities in the focal part of an utterance in Information Structure terms. These entities often introduce new information in discourse.</Paragraph>
    <Paragraph position="5"> In the present paper we describe an extended version of the dar-algorithm accounting for differences in the reference of various types of Danish demonstratives which we found analysing the uses of pronouns in three text collections (computer manuals, novels and newspaper articles) and three corpora of recorded naturally-occurring dialogues (the sl (Duncker and Hermann, 1996), the bysoc (Gregersen and Pedersen, 1991) and the pid corpora (Jensen, 1989)). In the following we first discuss the background for our proposal (section 2) then we describe the extended dar-algorithm (section 3). In section 4 we evaluate it and compare its performance with that of other known algorithms. Finally we make some concluding remarks.</Paragraph>
  </Section>
class="xml-element"></Paper>