Evaluating a focus-based approach to anaphora resolution

Abstract

We present an approach to anaphora resolution based on a focusing algorithm, and implemented within an existing MUC (Message Understanding Conference) Information Extraction system, allowing quantitative evaluation against a substantial corpus of annotated real-world texts. Extensions to the basic focusing mechanism can be easily tested, resulting in refinements to the mechanism and resolution rules. Results show that the focusing algorithm is highly sensitive to the quality of syntactic-semantic analyses, when compared to a simpler heuristic-based approach.1 This work was carried out in the context of the EU AVENTINUS project (Thurmair, 1996), which aims to develop a multilingual IE system for drug enforcement, and including a language-independent coreference mechanism .

A hierarchical account of referential accessibility

“…Here, we compare VT to stack-based models of discourse structure based on Grosz and Sidner's (1986) (G&S) focus spaces (e.g., Hahn and Strübe, 1997;Azzam, et al, 1998). In these approaches, discourse segments are pushed on the stack as they are encountered in a linear traversal of the text.…”

Evaluation-driven design of a robust coreference resolution system

“…The Centering Theory advocated a more fine-grained view of the focus stack and explored its relation to coherence among utterances (Grosz, Joshi and Weinstein 1995). The computation of the focus stack or of the centers requires more knowledge sources than those that were available to us -though simplified versions have been implemented by Azzam, Humphreys and Gaizauskas (1998) or Cristea et al (2002) for instance. We drew inspiration for our activation model from Alshawi's (1987) model of memory and his salience factors, adapted for pronominal anaphora resolution by Lappin and Leass (1994).…”

An Algorithm for Anaphora Resolution in Spanish Texts

“…Our approach to anaphora resolution belongs in the latter category, since it combines different kinds of knowledge and no knowledge based on discourse structure is included. We choose to ignore discourse structure because obtaining this kind of knowledge requires not only an understanding of semantics but also knowledge about world affairs and the ability to almost perfectly parse any text under discussion (Azzam, Humphreys, and Gaizauskas 1998).…”