Deep Reinforcement Learning for Mention-Ranking Coreference Models

EMNLP 2016  ·  Kevin Clark, Christopher D. Manning ·

Coreference resolution systems are typically trained with heuristic loss functions that require careful tuning. In this paper we instead apply reinforcement learning to directly optimize a neural mention-ranking model for coreference evaluation metrics. We experiment with two approaches: the REINFORCE policy gradient algorithm and a reward-rescaled max-margin objective. We find the latter to be more effective, resulting in significant improvements over the current state-of-the-art on the English and Chinese portions of the CoNLL 2012 Shared Task.

PDF Abstract EMNLP 2016 PDF EMNLP 2016 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Coreference Resolution OntoNotes Reward Rescaling F1 65.73 # 23

Methods


No methods listed for this paper. Add relevant methods here