Paper: An Expectation Maximization Approach To Pronoun Resolution

ACL ID W05-0612
Title An Expectation Maximization Approach To Pronoun Resolution
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2005
Authors

We propose an unsupervised Expectation Maximization approach to pronoun reso- lution. The system learns from a fixed list of potential antecedents for each pro- noun. We show that unsupervised learn- ing is possible in this context, as the per- formance of our system is comparable to supervised methods. Our results indicate that a probabilistic gender/number model, determined automatically from unlabeled text, is a powerful feature for this task.