<?xml version="1.0" standalone="yes"?>
<Paper uid="W97-1305">
  <Title>Resolving Anaphoric References on Deficient Syntactic Descriptions</Title>
  <Section position="2" start_page="0" end_page="30" type="intro">
    <SectionTitle>
1 Introduction
</SectionTitle>
    <Paragraph position="0"> The interpretation of anaphoric expressions is known to be a difficult problem. In principle, a variety of constraints and preference heuristics, including factors which rely on semantic, pragmatic, and world knowledge, contribute to this task (Carbonell and Brown, 1988). Operational approaches to anaphor resolution on unrestricted discourse, however, are confined to strategies exploiting globally available evidence like morphosyntactic, syntactic, and surface information.</Paragraph>
    <Paragraph position="1"> Among the most promising practical work are approaches relying on the availability of syntactic surface structure by employing coindexing restrictions, salience criteria, and parallelism heuristics (Lappin and Leass, 1994; Stuckardt, 1996b). However, even the assumption of the availability of a unique syntactic description is unrealistic since, in general, parsing involves the solution of difficult problems like attachment ambiguities, role uncertainty, and the instantiation of empty categories. Based on this observation, Kennedy and Boguraev suggest an adaptation of the Lappin and Leass approach to the analysis frontend of English Constraint Grammar (Karlsson et al., 1995), which provides a part-of-speech tagging comprising an assignment of syntactic function but no constituent structure. This information deficiency is partially overcome by the application of a regular filter which heuristically reconstructs constituent structure (Kennedy and Boguraev, 1996).</Paragraph>
    <Paragraph position="2"> The approach of Kennedy and Boguraev resorts to shallow input and heuristic reconstruction of surface structure in general, thus leaving open the question what may be gained by relying on the possibly partial, but potentially more reliable output of a conventional parser. This question is dealt with in the present paper. An operational approach to anaphor resolution is advocated which achieves robustness by a generalization to deficient syntactic descriptions rather than by resorting to shallow input. In section 2, notions of robustness are defined according to which different methods may be classified. Section 3 develops the perspective of fragmentary syntax and identifies the coindexing restrictions of binding theory as an important anaphor resolution strategy which is in particular affected by this loss of configurational evidence. In section 4, a solution is presented which accomplishes robustness against syntactic deficiency by a partly heuristic verification of coindexing constraints on fragmentary syntax. Finally, in section 5, a non-heuristic algorithm is specified which works on the standardized representation of ambiguous syntactic description by packed, shared parse forests. It achieves a higher degree of robustness by making available referential evidence  for a further disambiguation of syntactic structure.</Paragraph>
    <Paragraph position="3"> A combination of the two approaches is suggested as the practically optimal solution.</Paragraph>
  </Section>
class="xml-element"></Paper>