Supervised models for coreference resolution
Altaf Rahman, Vincent Ng · 2009
Traditional learning-based coreference resolvers operate by training a mention-pair classifier for determining whether two mentions are coreferent or not. Two independent lines of recent research have attempted to improve these mention-pair classifiers, one by learning a mention-ranking model to rank preceding mentions for a given anaphor, and the other by training an entity-mention classifier to determine whether a preceding cluster is coreferent with a given mention. We propose a cluster-ranking approach to coreference resolution that combines the strengths of mention rankers and entity-mention models. We additionally show how our cluster-ranking framework naturally allows discourse-new entity detection to be learned jointly with coreference resolution. Experimental results on the ACE data sets demonstrate its superior performance to competing approaches.