mlsanityData to 7 Oct 2026

Reinforcement Learning based Curriculum Optimization for Neural Machine Translation

arXiv 1903.00041 ↗First posted 28 Feb 2019cs.CLcited by 29

Not on the map. Why?

Abstract (arXiv)

We consider the problem of making efficient use of heterogeneous training data in neural machine translation (NMT). Specifically, given a training dataset with a sentence-level feature such as noise, we seek an optimal curriculum, or order for presenting examples to the system during training. Our curriculum framework allows examples to appear an arbitrary number of times, and thus generalizes data weighting, filtering, and fine-tuning schemes. Rather than relying on prior knowledge to design a curriculum, we use reinforcement learning to learn one automatically, jointly with the NMT system, in the course of a single training run. We show that this approach can beat uniform and filtering baselines on Paracrawl and WMT English-to-French datasets by up to +3.4 BLEU, and match the performance of a hand-designed, state-of-the-art curriculum.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 9; 2023: 6; 2024: 3; 2025: 2; 2026: 2.

29 papers.

Sort:

By area:

  1. 2021Curriculum Learning: A Surveycited by 257
  2. 2023Guiding Large Language Models via Directional Stimulus Promptingcited by 94
  3. 2022Competence-based Multimodal Curriculum Learning for Medical Report Generationcited by 74
  4. 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
  5. 2022An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Modelscited by 20
  6. 2023Make Every Example Count: On the Stability and Utility of Self-Influence for Learning from Noisy NLP Datasetscited by 18
  7. 2021Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Banditscited by 16
  8. 2022Data Selection Curriculum for Neural Machine Translationcited by 11
  9. 2023Adaptive Training Distributions with Scalable Online Bilevel Optimizationcited by 11
  10. 2021On the Complementarity of Data Selection and Fine Tuning for Domain Adaptationcited by 10
  11. 2022Generative Entity Typing with Curriculum Learningcited by 8
  12. 2022Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine Translationcited by 8
17 more
  1. 2024A Psychology-based Unified Dynamic Framework for Curriculum Learningcited by 6
  2. 2022Training Dynamics for Curriculum Learning: A Study on Monolingual and Cross-lingual NLUcited by 5
  3. 2021Token-wise Curriculum Learning for Neural Machine Translationcited by 4
  4. 2022In-sample Curriculum Learning by Sequence Completion for Natural Language Generationcited by 4
  5. 2023Robust Positive-Unlabeled Learning via Noise Negative Sample Self-correctioncited by 4
  6. 2026Mending the Holes: Mitigating Reward Hacking in Reinforcement Learning for Multilingual Translationcited by 3
  7. 2025Searching the Internet for Challenging Benchmarks at Scalecited by 2
  8. 2021Learning Policies for Multilingual Training of Neural Machine Translation Systemscited by 1
  9. 2021Learning Feature Weights using Reward Modeling for Denoising Parallel Corporacited by 1
  10. 2022Curriculum optimization for low-resource speech recognitioncited by 1
  11. 2022Efficient Distributed Framework for Collaborative Multi-Agent Reinforcement Learningcited by 1
  12. 2023Progressively Efficient Learningcited by 1
  13. 2024LexMatcher: Dictionary-centric Data Collection for LLM-based Machine Translationcited by 1
  14. 2025Adaptively Point-weighting Curriculum Learningcited by 1
  15. 2023Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translationcited by 0
  16. 2024Optimizing the Training Schedule of Multilingual NMT using Reinforcement Learningcited by 0
  17. 2026Disentangling Curriculum Learning in NLP: Towards a Unifying Taxonomycited by 0