Paper: Bootstrapping Path-Based Pronoun Resolution

ACL ID P06-1005
Title Bootstrapping Path-Based Pronoun Resolution
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2006

We present an approach to pronoun reso- lution based on syntactic paths. Through a simple bootstrapping procedure, we learn the likelihood of coreference between a pronoun and a candidate noun based on the path in the parse tree between the two en- tities. This path information enables us to handle previously challenging resolution instances, and also robustly addresses tra- ditional syntactic coreference constraints. Highly coreferent paths also allow mining of precise probabilistic gender/number in- formation. We combine statistical knowl- edge with well known features in a Sup- port Vector Machine pronoun resolution classi er. Signi cant gains in performance are observed on several datasets.