Anaphora in a Wider Context: Tracking Discourse Referents
Christopher B. Kennedy, Branimir Boguraev · 1996
Abstract. A number of linguistic and stylistic devices are employed in text-based discourse for the purposes of introducing, defining, re-fining, and re-introducing discourse entities. This paper looks at one of the most pervasive of these mechanisms, anaphora, and addresses the question of how current computational approaches to anaphora scale up to building, and maintaining, a richer model of text struc-ture, which embodies the notion of a discourse referent’s behaviour in the entire text. Given the less than fully robust status of syntac-tic parsers to date, we question the applicability of current anaphora resolution algorithms to open-ended text types, styles, and genres. We outline an algorithm for anaphora resolution, which modifieds and extends a configurationally-based approach, while working from the output of a part of speech tagger, enriched only with annotations of grammatical function. Without compromising output quality, the algorithm compensates for the shallower level of analysis with mech-