mlsanityData to 7 Oct 2026

Minimum Risk Training for Neural Machine Translation

arXiv 1512.02433 ↗First posted 8 Dec 2015cs.CLcited by 114

Not on the map. Why?

Abstract (arXiv)

We propose minimum risk training for end-to-end neural machine translation. Unlike conventional maximum likelihood estimation, minimum risk training is capable of optimizing model parameters directly with respect to arbitrary evaluation metrics, which are not necessarily differentiable. Experiments show that our approach achieves significant improvements over maximum likelihood estimation on a state-of-the-art neural machine translation system across various languages pairs. Transparent to architectures, our approach can be applied to more neural networks and potentially benefit more NLP tasks.

Key facts. Cited by 114 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Dec 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 1; 2020: 1; 2021: 34; 2022: 21; 2023: 28; 2024: 12; 2025: 9; 2026: 7.

114 papers.

Sort:

By area:

  1. 2022Quark: Controllable Text Generation with Reinforced Unlearningcited by 236
  2. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
  3. 2023ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Modelscited by 184
  4. 2022BRIO: Bringing Order to Abstractive Summarizationcited by 161
  5. 2021SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarizationcited by 131
  6. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 129
  7. 2022Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generationcited by 106
  8. 2021Survey of Low-Resource Machine Translationcited by 92
  9. 2024RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMscited by 89
  10. 2023On Learning to Summarize with Large Language Models as Referencescited by 80
  11. 2023RMM: Reinforced Memory Management for Class-Incremental Learningcited by 66
  12. 2020Text Generation by Learning from Demonstrationscited by 64
38 more
  1. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  2. 2018Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learningcited by 57
  3. 2021Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translationcited by 57
  4. 2021Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translationcited by 56
  5. 2021Machine Translation Decoding beyond Beam Searchcited by 55
  6. 2023Bridging the Gap: A Survey on Integrating (Human) Feedback for Natural Language Generationcited by 55
  7. 2022LENS: A Learnable Evaluation Metric for Text Simplificationcited by 54
  8. 2022Quality-Aware Decoding for Neural Machine Translationcited by 49
  9. 2023Learning to Generate Better Than Your LLMcited by 49
  10. 2023It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Riskcited by 49
  11. 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
  12. 2022Rainier: Reinforced Knowledge Introspector for Commonsense Question Answeringcited by 43
  13. 2022Identifying Weaknesses in Machine Translation Metrics Through Minimum Bayes Risk Decoding: A Case Study for COMETcited by 41
  14. 2023Tuning computer vision models with task rewardscited by 36
  15. 2021Prevent the Language Model from being Overconfident in Neural Machine Translationcited by 34
  16. 2023MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methodscited by 33
  17. 2024Improving Machine Translation with Human Feedback: An Exploration of Quality Estimation as a Reward Modelcited by 33
  18. 2021Revisiting the Weaknesses of Reinforcement Learning for Neural Machine Translationcited by 32
  19. 2023Gender Biases in Automatic Evaluation Metrics for Image Captioningcited by 24
  20. 2023BLEURT Has Universal Translations: An Analysis of Automatic Metrics by Minimum Risk Trainingcited by 24
  21. 2021AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Taskscited by 19
  22. 2023Aligning Neural Machine Translation Models: Human Feedback in Training and Inferencecited by 19
  23. 2021Sequence-Level Training for Non-Autoregressive Neural Machine Translationcited by 18
  24. 2021Don't Take It Literally: An Edit-Invariant Sequence Loss for Text Generationcited by 17
  25. 2021Modelling Latent Translations for Cross-Lingual Transfercited by 16
  26. 2021Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Banditscited by 16
  27. 2024QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translationcited by 16
  28. 2023Understanding and Bridging the Modality Gap for Speech Translationcited by 15
  29. 2023ESRL: Efficient Sampling-based Reinforcement Learning for Sequence Generationcited by 15
  30. 2021Reward Optimization for Neural Machine Translation with Learned Metricscited by 12
  31. 2019An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generationcited by 11
  32. 2021Smoothing and Shrinking the Sparse Seq2Seq Search Spacecited by 11
  33. 2021Scheduled Sampling Based on Decoding Steps for Neural Machine Translationcited by 11
  34. 2021Conditional Poisson Stochastic Beam Searchcited by 11
  35. 2022Teacher Forcing Recovers Reward Functions for Text Generationcited by 11
  36. 2024Fine-Grained Reward Optimization for Machine Translation using Error Severity Mappingscited by 11
  37. 2021Confidence-Aware Scheduled Sampling for Neural Machine Translationcited by 10
  38. 2023Can Diffusion Model Achieve Better Performance in Text Generation? Bridging the Gap between Training and Inference!cited by 10

50 most cited of 114 All 114 (JSON)