Supervised Models for Coreference Resolution

9 years 1 months ago
Supervised Models for Coreference Resolution
Traditional learning-based coreference resolvers operate by training a mentionpair 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 mentionranking 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 entitymention models. We additionally show how our cluster-ranking framework naturally allows anaphoricity determination to be learned jointly with coreference resolution. Experimental results on the ACE data sets demonstrate its superior performance to competing approaches.
Md. Altaf ur Rahman, Vincent Ng
Added 17 Feb 2011
Updated 17 Feb 2011
Type Journal
Year 2009
Authors Md. Altaf ur Rahman, Vincent Ng
Comments (0)