End-to-end Deep Reinforcement Learning Based Coreference Resolution
Hongliang Fei, Li Hong Xu, Dingcheng Li, Ping Li · 2019
Recent neural network models have significantly advanced the task of coreference resolution.However, current neural coreference models are typically trained with heuristic loss functions that are computed over a sequence of local decisions.In this paper, we introduce an end-to-end reinforcement learning based coreference resolution model to directly optimize coreference evaluation metrics.Specifically, we modify the state-of-the-art higherorder mention ranking approach in Lee et al. (2018) to a reinforced policy gradient model by incorporating the reward associated with a sequence of coreference linking actions.Furthermore, we introduce maximum entropy regularization for adequate exploration to prevent the model from prematurely converging to a bad local optimum.Our proposed model achieves new state-of-the-art performance on the English OntoNotes v5.0 benchmark.