Deep Reinforcement Learning for Mention-Ranking Coreference Models
Kevin Clark, Christopher D. Manning
2016-09-27EMNLP 2016 11coreference-resolutionReinforcement LearningCoreference Resolutionreinforcement-learning
Abstract
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.
Results
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Coreference Resolution | OntoNotes | F1 | 65.73 | Reward Rescaling |
Related Papers
CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning2025-07-18VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning2025-07-17Spectral Bellman Method: Unifying Representation and Exploration in RL2025-07-17Aligning Humans and Robots via Reinforcement Learning from Implicit Human Feedback2025-07-17VAR-MATH: Probing True Mathematical Reasoning in Large Language Models via Symbolic Multi-Instance Benchmarks2025-07-17QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation2025-07-17Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities2025-07-17Autonomous Resource Management in Microservice Systems via Reinforcement Learning2025-07-17