Discourse anaphora

  • Authors:
  • Joke Dorrepaal

  • Affiliations:
  • OTS RUU Utrecht

  • Venue:
  • COLING '90 Proceedings of the 13th conference on Computational linguistics - Volume 2
  • Year:
  • 1990

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper reports on a model that serves anaphora resolution. A distinction will be made between possible antecedents and preferred antecedents. The set of linguistically possible candidates will be defined in terms of compatibility and recency. Preferred antecedents are a subset of the possible antecedents, selected by the application of extralinguistic knowledge. Motivation for the particular design and comparison with other approaches are extensive.