ABSTRACT
This paper describes research into the application of machine learning techniques to the resolution of anaphoric reference. While a number of theories have been proposed for certain classes of anaphors (e.g. centring: Brennan et al. 1987; Grosz & Sidner 1986), reference resolution remains a difficult problem in the general case and continues to be a major hurdle on the critical path to robust, end-to-end language processing. In this research, we have attempted to cast anaphoric reference as a classification problem for which a classifier can be discovered empirically using traditional learning methods.
