mlsanityData to 7 Oct 2026

An Empirical Exploration of Curriculum Learning for Neural Machine Translation

arXiv 1811.00739 ↗First posted 2 Nov 2018cs.CL cs.LGcited by 58

Not on the map. Why?

Abstract (arXiv)

Machine translation systems based on deep neural networks are expensive to train. Curriculum learning aims to address this issue by choosing the order in which samples are presented during training to help train better models faster. We adopt a probabilistic view of curriculum learning, which lets us flexibly evaluate the impact of curricula design, and perform an extensive exploration on a German-English translation task. Results show that it is possible to improve convergence time at no loss in translation quality. However, results are highly sensitive to the choice of sample difficulty criteria, curriculum schedule and other hyperparameters.

Key facts. Cited by 58 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 15; 2023: 10; 2024: 10; 2025: 6; 2026: 2.

58 papers.

Sort:

By area:

  1. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 552
  2. 2021Curriculum Learning: A Surveycited by 257
  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. 2022EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbonescited 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. 2021Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translationcited by 28
  9. 2021Bridging Pre-trained Models and Downstream Tasks for Source Code Understandingcited by 27
  10. 2025Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learningcited 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. 2022An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Modelscited by 20
  2. 2021Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Banditscited by 16
  3. 2024EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Trainingcited by 16
  4. 2023A Systematic Review of Deep Learning-based Research on Radiology Report Generationcited by 14
  5. 2022DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routingcited by 13
  6. 2022Efficient Pre-training of Masked Language Model via Concept-based Curriculum Maskingcited by 12
  7. 2023Curricular Object Manipulation in LiDAR-based Object Detectioncited by 12
  8. 2022Data Selection Curriculum for Neural Machine Translationcited by 11
  9. 2021Self-Guided Curriculum Learning for Neural Machine Translationcited by 9
  10. 2022When Do Curricula Work in Federated Learning?cited by 9
  11. 2022Self-paced Multi-grained Cross-modal Interaction Modeling for Referring Expression Comprehensioncited by 8
  12. 2022Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine Translationcited by 8
  13. 2023GaitMPL: Gait Recognition with Memory-Augmented Progressive Learningcited by 7
  14. 2021Exploiting Curriculum Learning in Unsupervised Neural Machine Translationcited by 6
  15. 2023Too Much Information: Keeping Training Simple for BabyLMscited by 6
  16. 2024HiCuLR: Hierarchical Curriculum Learning for Rhetorical Role Labeling of Legal Documentscited by 6
  17. 2025Estimating Machine Translation Difficultycited by 6
  18. 2022From Easy to Hard: A Dual Curriculum Learning Framework for Context-Aware Document Rankingcited by 5
  19. 2022Training Dynamics for Curriculum Learning: A Study on Monolingual and Cross-lingual NLUcited by 5
  20. 2021Token-wise Curriculum Learning for Neural Machine Translationcited by 4
  21. 2022Improving Neural Machine Translation by Denoising Trainingcited by 4
  22. 2022Cyclical Curriculum Learningcited by 4
  23. 2022In-sample Curriculum Learning by Sequence Completion for Natural Language Generationcited by 4
  24. 2024Let's Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Modelscited by 4
  25. 2021Do Data-based Curricula Work?cited by 3
  26. 2022Confidence-Guided Learning Process for Continuous Classification of Time Seriescited by 3
  27. 2025Continual learning for rotating machinery fault diagnosis with cross-domain environmental and operational variationscited by 3
  28. 2025You Are What You Train: Effects of Data Composition on Training Context-aware Machine Translation Modelscited by 3
  29. 2023Confidence-Aware Calibration and Scoring Functions for Curriculum Learningcited by 2
  30. 2021Statistical Measures For Defining Curriculum Scoring Functioncited by 1
  31. 2021Learning Policies for Multilingual Training of Neural Machine Translation Systemscited by 1
  32. 2023Token-Level Fitting Issues of Seq2seq Modelscited by 1
  33. 2023Simple and Effective Input Reformulations for Translationcited by 1
  34. 2024Vygotsky Distance: Measure for Benchmark Task Similaritycited by 1
  35. 2024False Positive Sampling-based Data Augmentation for Enhanced 3D Object Detection Accuracycited by 1
  36. 2024Curriculum Learning for Cross-Lingual Data-to-Text Generation With Noisy Datacited by 1
  37. 2021Curriculum generation using Autoencoder based continuous optimizationcited by 0
  38. 2023A Curriculum View of Robust Loss Functionscited by 0

50 most cited of 58 All 58 (JSON)