Paper: Prune-and-Score: Learning for Greedy Coreference Resolution

ACL ID D14-1225
Title Prune-and-Score: Learning for Greedy Coreference Resolution
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2014

We propose a novel search-based approach for greedy coreference resolution, where the mentions are processed in order and added to previous coreference clusters. Our method is distinguished by the use of two functions to make each corefer- ence decision: a pruning function that prunes bad coreference decisions from fur- ther consideration, and a scoring function that then selects the best among the re- maining decisions. Our framework re- duces learning of these functions to rank learning, which helps leverage powerful off-the-shelf rank-learners. We show that our Prune-and-Score approach is superior to using a single scoring function to make both decisions and outperforms sever- al state-of-the-art approaches on multiple benchmark corpora including OntoNotes.