CogNIAC : A High Precision Pronoun Resolution Engine

This paper presents a high precision pronoun resolution system that is capable of greater than 90% precision with 60% and better recall for some pronouns. It is suggested that the system is resolving a sub-set of anaphors that do not require general world knowledge for successful resolution. The system does this by being very sensitive to ambiguity, and only resolving pronouns when very high confidence rules have been satisfied. The system is capable of 'noticing' ambiguity because it requires that there be a unique antecedent within a salience ranking, and the salience rankings are not total orders, i.e. two or more antecedents can be equally salient. The system has been evaluated in three distinct experiments which support the overall validity of the approach. 1 Introduction Pronoun resolution is one of the 'classic' computational linguistics problems. It is also widely considered to be inherently an 'A.I. complete' task--meaning that resolution of pronouns requires full world knowl..