An algorithm for pronominal anaphora resolution

This paper presents an algorithm for identifying the noun phrase antecedents of third person pronouns and lexical anaphors (reflexives and reciprocals). The algorithm applies to the syntactic representations generated by McCords Slot Grammar parser and relies on salience measures derived from syntactic structure and a simple dynamic model of attentional state. Like the parser, the algorithm is implemented in Prolog. The authors have tested it extensively on computer manual texts and conducted a blind test on manual text containing 360 pronoun occurrences. The algorithm successfully identifies the antecedent of the pronoun for 86% of these pronoun occurrences. The relative contributions of the algorithms components to its overall success rate in this blind test are examined. Experiments were conducted with an enhancement of the algorithm that contributes statistically modelled information concerning semantic and real-world relations to the algorithms decision procedure. Interestingly, this enhancement only marginally improves the algorithms performance (by 2 %). The algorithm is compared with other approaches to anaphora resolution that have been proposed in the literature. In particular, the search procedure of Hobbsalgorithm was implemented in the Slot Grammar framework and applied to the sentences in the blind test set. The authors algorithm achieves a higher rate of success (4%) than Hobbs algorithm. The relation of the algorithm to the centering approach is discussed, as well as to models of anaphora resolution that invoke a variety of informational factors in ranking antecedent candidates