mlsanityData to 7 Oct 2026

Curriculum Learning and Minibatch Bucketing in Neural Machine Translation

arXiv 1707.09533 ↗First posted 29 Jul 2017cs.CLcited by 63

Not on the map. Why?

Abstract (arXiv)

We examine the effects of particular orderings of sentence pairs on the on-line training of neural machine translation (NMT). We focus on two types of such orderings: (1) ensuring that each minibatch contains sentences similar in some aspect and (2) gradual inclusion of some sentence types as the training progresses (so called "curriculum learning"). In our English-to-Czech experiments, the internal homogeneity of minibatches has no effect on the training but some of our "curricula" achieve a small improvement over the baseline.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 9; 2023: 16; 2024: 10; 2025: 7; 2026: 6.

63 papers.

Sort:

By area:

  1. 2021Curriculum Learning: A Surveycited by 257
  2. 2022Competence-based Multimodal Curriculum Learning for Medical Report Generationcited by 74
  3. 2023Generalization on the Unseen, Logic Reasoning and Degree Curriculumcited by 73
  4. 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
  5. 2021Selective Knowledge Distillation for Neural Machine Translationcited by 42
  6. 2021The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Modelscited by 36
  7. 2021Does the Order of Training Samples Matter? Improving Neural Data-to-Text Generation with Curriculum Learningcited by 34
  8. 2021An Analytical Theory of Curriculum Learning in Teacher-Student Networkscited by 27
  9. 2021Bridging Pre-trained Models and Downstream Tasks for Source Code Understandingcited by 27
  10. 2023The Efficiency Spectrum of Large Language Models: An Algorithmic Surveycited by 25
  11. 2023Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputscited by 22
  12. 2021Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absentcited by 21
38 more
  1. 2023CLIMB: Curriculum Learning for Infant-inspired Model Buildingcited by 20
  2. 2023Coaching a Teachable Studentcited by 17
  3. 2021Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Banditscited by 16
  4. 2024Boost Your Human Image Generation Model via Direct Preference Optimizationcited by 16
  5. 2022Contextual Similarity is More Valuable than Character Similarity: An Empirical Study for Chinese Spell Checkingcited by 14
  6. 2022DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routingcited by 13
  7. 2024Intent-based Prompt Calibration: Enhancing prompt optimization with synthetic boundary casescited by 13
  8. 2023Curricular Object Manipulation in LiDAR-based Object Detectioncited by 12
  9. 2022Data Selection Curriculum for Neural Machine Translationcited by 11
  10. 2021Self-Guided Curriculum Learning for Neural Machine Translationcited by 9
  11. 2022Learning Rate Curriculumcited by 9
  12. 2023SteloCoder: a Decoder-Only LLM for Multi-Language to Python Code Translationcited by 9
  13. 2021Competence-based Curriculum Learning for Multilingual Machine Translationcited by 8
  14. 2022Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine Translationcited by 8
  15. 2024Effective Generative AI: The Human-Algorithm Centaurcited by 8
  16. 2023Curriculum-Based Augmented Fourier Domain Adaptation for Robust Medical Image Segmentationcited by 7
  17. 2023Reverse Stable Diffusion: What prompt was used to generate this image?cited by 7
  18. 2021Exploiting Curriculum Learning in Unsupervised Neural Machine Translationcited by 6
  19. 2023Digital Twin-based Anomaly Detection with Curriculum Learning in Cyber-physical Systemscited by 6
  20. 2023Too Much Information: Keeping Training Simple for BabyLMscited by 6
  21. 2024A Psychology-based Unified Dynamic Framework for Curriculum Learningcited by 6
  22. 2024HiCuLR: Hierarchical Curriculum Learning for Rhetorical Role Labeling of Legal Documentscited by 6
  23. 2025Estimating Machine Translation Difficultycited by 6
  24. 2022Training Dynamics for Curriculum Learning: A Study on Monolingual and Cross-lingual NLUcited by 5
  25. 2024Re-Examine Distantly Supervised NER: A New Benchmark and a Simple Approachcited by 5
  26. 2021Token-wise Curriculum Learning for Neural Machine Translationcited by 4
  27. 2022Cyclical Curriculum Learningcited by 4
  28. 2022In-sample Curriculum Learning by Sequence Completion for Natural Language Generationcited by 4
  29. 2025Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferralcited by 4
  30. 2021Do Data-based Curricula Work?cited by 3
  31. 2023Curriculum Learning with Adam: The Devil Is in the Wrong Detailscited by 3
  32. 2024CBM: Curriculum by Maskingcited by 3
  33. 2025Task-Informed Anti-Curriculum by Masking Improves Downstream Performance on Textcited by 3
  34. 2025Understanding Complexity in VideoQA via Visual Program Generationcited by 3
  35. 2023Confidence-Aware Calibration and Scoring Functions for Curriculum Learningcited by 2
  36. 2025Efficient Knowledge Distillation via Curriculum Extractioncited by 2
  37. 2021Statistical Measures For Defining Curriculum Scoring Functioncited by 1
  38. 2023Token-Level Fitting Issues of Seq2seq Modelscited by 1

50 most cited of 63 All 63 (JSON)