<?xml version="1.0" standalone="yes"?>
<Paper uid="C00-2133">
  <Title>Prosody and the Resolution of Pronominal Anaphora</Title>
  <Section position="3" start_page="0" end_page="919" type="intro">
    <SectionTitle>
2 Background and Related Work
</SectionTitle>
    <Paragraph position="0"> There is a rich literature C/)11 resolving personal pronouns.</Paragraph>
    <Paragraph position="1"> Many approaches arc based on a notion of attentional foctls. Entities in attentional focus are highly salient, and pronouns are assumed to refer to tile most salient entity in lhc discourse (el. (Brennan el al., 1987; Azzam et ill., 1998; Strube, 1998)). Centering (Grosz et al., 1995) is a i}amework for predicting local attentional focus. It assumes that tile most salient entity from sentence ,3,,_\] that is realized in sentence ,5',, is most likely to be pronominalized in ,3,z. That entity is termed the Cb (backward-looking center) of sentence ,5',,. Finding ille preferred ranking criteria is an active area of research.</Paragraph>
    <Paragraph position="2"> Byron and Stem (1998) adapted this approach, which had previously been applied to text, for spoken dialogs, but wilh linfited st,ccess.</Paragraph>
    <Paragraph position="3"> \]n contrast to personal pronouns, demonstratives do not rely on calculalions of salience. In fact, Linde (1979) found lhat while it was preferred for entities within the  current local t'ocus, that was used for items outside the current focus of attention. Passonneau (1989) showed that personal and demonstrative pronouns are used in contrasting situations: personal pronouns are preferred when both the pronoun and its antecedent are in sub-ject position, while demonstrative pronouns are preferred when either the pronoun or its antecedent is not ill sub-ject position. She also found that personal pronouns tend to co-specify with pronouns or base noun phrases; the more clause- or seutence-likc the antecedent, the more likely the speaker is to choose a demonstrative pronoun.</Paragraph>
    <Paragraph position="4"> Pronoun resolution algoritlnns tend not to cover demonstratives. Notable exceptions are Webber's model for discotn'se deixis (Webbcr, 1991) and the model developed for spoken dialog by Eekert and Strube (1999).</Paragraph>
    <Paragraph position="5"> This algorithm encompasses both personal and delnonstrative pronouns and exploits their contrastive usage patterns, relying on syntactic clues and verb subcategorizations as input. Neither study investigated the intluence of prosodic prominence on resolution.</Paragraph>
    <Paragraph position="6"> Most previous work on prosody and pronotm resolution has focussed on pitch accents and third person singular pronouns that co-specify with persons. Nakatani (1997) examined the antecedents of personal pronouns in a 20-minute narrative monologue. She found that pronouns tend to be accented il' they occur in subject position, and if the backward-looking center (Grosz et al., 1995) was shifted to the referent of that pronoun. She then extended this result to a general theory of the interaction between l)rominencc and discourse structure.</Paragraph>
    <Paragraph position="7"> Cahu (1995)discusses accented prorJouns on the basis of a theory about accentual correlates of salience.</Paragraph>
    <Paragraph position="8"> Kamcyama (1998) interprets a pitch accent on pronouns in the fl'amework of Ihe alternative semantics (Rooth, 1992) theory o1' focus. She assumes that all potential antecedents are stored in a list. Pronouns arc then resolved to the most preferred antecedent on that list which is syntactically and semantically compatible with the pronoun.</Paragraph>
    <Paragraph position="9"> Preference is modeled by an ordering on the set ol' antecedents. An accent on lhe pronoun signals that pronoun resolution should not be based on the default ordering, where the default is computed by a nmnber of interacting syntactic, semantic, pragmatic, and attentional constraints.</Paragraph>
    <Paragraph position="10"> Compared to he and she, it and that lmve been somewhat neglected. There are two reasons for this: First, it is not considered to be as accentable as he and she by native speakers of both British and American English, whereas that is more likely than it to beat&amp;quot; a pitch accent. An informal study of the London-Lund corptts of spoken British English (Svartvik, 1990) confirmed that observation. Second, that fi'cquently does not lmve a co-specifying NP antecedent, and most research on cospeciticatiou has focussed on pronouns and NPs. Work on accented demonstratives and pronoun resolution is extremely scarce. Pioneering studies were conducted by Ft'ethcim and his collaborators. They tested the effect of accented sentence-initial demonstratives that co-specify with the preceding sentence on the resolution of ambiguous personal pronouns, and found that the pronoun antecedents switched when the demonstrative was accented (Fretheim ct al., 1997). However, to otu&amp;quot; knowledge, there are no studies that compare the co-specification preferences of accented vs. unaccented demonstratives.</Paragraph>
  </Section>
class="xml-element"></Paper>