Papers › End-to-end Deep Reinforcement Learning Based Coreference Resolution

End-to-end Deep Reinforcement Learning Based Coreference Resolution

1 Jul 2019ACL 2019 7archive 2025-07-28

Hongliang Fei, Xu Li, Dingcheng Li, Ping Li

Recent neural network models have significantly advanced the task of coreference resolution. However, current neural coreference models are usually 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 higher-order 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.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Coreference ResolutionDeep Reinforcement LearningReinforcement LearningReinforcement Learning (RL)coreference-resolutionreinforcement-learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Coreference Resolution CoNLL 2012 reinforced model + ELMO Avg F1 73.8 #14 of 18 Archive leaderboard report
Coreference Resolution OntoNotes Reinforced + ELMo F1 73.8 #18 of 26 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Entropy Regularization

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections