mlsanityData to 14 Oct 2026

A Study of Reinforcement Learning for Neural Machine Translation

arXiv 1808.08866 ↗First posted 27 Aug 2018cs.LG cs.AI stat.MLcited by 74

Not on the map. Why?

Abstract (arXiv)

Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation (NMT) system. However, due to its instability, successfully RL training is challenging, especially in real-world systems where deep models and large datasets are leveraged. In this paper, taking several large-scale translation tasks as testbeds, we conduct a systematic study on how to train better NMT models using reinforcement learning. We provide a comprehensive comparison of several important factors (e.g., baseline reward, reward shaping) in RL training. Furthermore, to fill in the gap that it remains unclear whether RL is still beneficial when monolingual data is used, we propose a new method to leverage RL to further boost the performance of NMT systems trained with source/target monolingual data. By integrating all our findings, we obtain competitive results on WMT14 English- German, WMT17 English-Chinese, and WMT17 Chinese-English translation tasks, especially setting a state-of-the-art performance on WMT17 Chinese-English translation task.

Key facts. Cited by 74 papers in the map (data through 14 Oct 2026). First posted on arXiv 27 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2019: 1; 2020: 1; 2021: 22; 2022: 16; 2023: 14; 2024: 11; 2025: 7; 2026: 2.

74 papers.

Sort:

By area:

  1. 2023On-Policy Distillation of Language Models: Learning from Self-Generated Mistakescited by 939
  2. 2023RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackcited by 625
  3. 2023REFINER: Reasoning Feedback on Intermediate Representationscited by 205
  4. 2021Neural Machine Translation for Low-Resource Languages: A Surveycited by 109
  5. 2023Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedbackcited by 72
  6. 2020Text Generation by Learning from Demonstrationscited by 64
  7. 2022A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyondcited by 64
  8. 2025MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learningcited by 48
  9. 2021Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphscited by 39
  10. 2021Efficient (Soft) Q-Learning for Text Generation with Limited Good Datacited by 37
  11. 2021Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translationcited by 33
  12. 2024Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Modelcited by 33
38 more
  1. 2021Survey on reinforcement learning for language processingcited by 31
  2. 2023Tailoring Language Generation Models under Total Variation Distancecited by 27
  3. 2023The Eval4NLP 2023 Shared Task on Prompting Large Language Models as Explainable Metricscited by 23
  4. 2021AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Taskscited by 19
  5. 2023Aligning Neural Machine Translation Models: Human Feedback in Training and Inferencecited by 19
  6. 2021Sequence-Level Training for Non-Autoregressive Neural Machine Translationcited by 18
  7. 2021Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generationcited by 17
  8. 2025BLEUBERI: BLEU is a surprisingly effective reward for instruction followingcited by 17
  9. 2021Reinforced Iterative Knowledge Distillation for Cross-Lingual Named Entity Recognitioncited by 15
  10. 2023Understanding and Bridging the Modality Gap for Speech Translationcited by 15
  11. 2023Towards Explainable Evaluation Metrics for Machine Translationcited by 15
  12. 2021Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learningcited by 13
  13. 2024Advancing Translation Preference Modeling with RLHF: A Step Towards Cost-Effective Solutioncited by 13
  14. 2021Reward Optimization for Neural Machine Translation with Learned Metricscited by 12
  15. 2024Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewardscited by 12
  16. 2019An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generationcited by 11
  17. 2023Metric-oriented Speech Enhancement using Diffusion Probabilistic Modelcited by 11
  18. 2023Reinforcement Learning for Generative AI: A Surveycited by 11
  19. 2024Fine-Grained Reward Optimization for Machine Translation using Error Severity Mappingscited by 11
  20. 2021Constrained Text Generation with Global Guidance -- Case Study on CommonGencited by 10
  21. 2021Unsupervised Contextual Paraphrase Generation using Lexical Control and Reinforcement Learningcited by 10
  22. 2021Guiding Teacher Forcing with Seer Forcing for Neural Machine Translationcited by 8
  23. 2021Learning from Executions for Semantic Parsingcited by 7
  24. 2022Efficient Reinforcement Learning for Unsupervised Controlled Text Generationcited by 7
  25. 2022MAD for Robust Reinforcement Learning in Machine Translationcited by 7
  26. 2024LLM-based Rewriting of Inappropriate Argumentation using Reinforcement Learning from Machine Feedbackcited by 7
  27. 2021Nutri-bullets: Summarizing Health Studies by Composing Segmentscited by 6
  28. 2022Multi-Granularity Optimization for Non-Autoregressive Translationcited by 6
  29. 2022Language Model Decoding as Likelihood-Utility Alignmentcited by 5
  30. 2024Beyond Accuracy Optimization: Computer Vision Losses for Large Language Model Fine-Tuningcited by 5
  31. 2022Joint Generator-Ranker Learning for Natural Language Generationcited by 4
  32. 2022Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learningcited by 4
  33. 2022DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decodingcited by 4
  34. 2024Safe Reinforcement Learning with Free-form Natural Language Constraints and Pre-Trained Language Modelscited by 4
  35. 2025RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translationcited by 4
  36. 2021Simpson's Bias in NLP Trainingcited by 3
  37. 2021Diversity-Driven Combination for Grammatical Error Correctioncited by 3
  38. 2022Rephrasing the Reference for Non-Autoregressive Machine Translationcited by 3

50 most cited of 74 All 74 (JSON)