Year: 2006
Type: conference-paper
Abstract: We present an approach to pronoun resolution 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 entities. This path information enables us to handle previously challenging resolution instances, and also robustly addresses traditional syntactic coreference constraints. Highly coreferent paths also allow mining of precise probabilistic gender/number information. We combine statistical knowledge with well known features in a Support Vector Machine pronoun resolution classifier. Significant gains in performance are observed on several datasets.
Authors: Shane Bergsma, Dekang Lin
Institutions: University of Alberta, Google (United States)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
OpenAlex ID: W2099115159