mlsanityData to 7 Oct 2026

Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation

arXiv 2103.02262 ↗First posted 3 Mar 2021cs.CL cs.LGcited by 28

Not on the map. Why?

Abstract (arXiv)

Meta-learning has been sufficiently validated to be beneficial for low-resource neural machine translation (NMT). However, we find that meta-trained NMT fails to improve the translation performance of the domain unseen at the meta-training stage. In this paper, we aim to alleviate this issue by proposing a novel meta-curriculum learning for domain adaptation in NMT. During meta-training, the NMT first learns the similar curricula from each domain to avoid falling into a bad local optimum early, and finally learns the curricula of individualities to improve the model robustness for learning domain-specific knowledge. Experimental results on 10 different low-resource domains show that meta-curriculum learning can improve the translation performance of both familiar and unfamiliar domains. All the codes and data are freely available at https://github.com/NLP2CT/Meta-Curriculum.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 21 of its 32 references that are in the map. First posted on arXiv 3 Mar 2021.

Builds on

21 of 32 references.

References · 21

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  6. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  7. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
  8. 2018On First-Order Meta-Learning Algorithmscited by 1,003
  9. 2017Six Challenges for Neural Machine Translationcited by 334
  10. 2019Competence-based Curriculum Learning for Neural Machine Translationcited by 201
  11. 2018Meta-Learning for Low-Resource Neural Machine Translationcited by 105
  12. 2018A Survey of Domain Adaptation for Neural Machine Translationcited by 64
9 more
  1. 2020Norm-Based Curriculum Learning for Neural Machine Translationcited by 60
  2. 2019Curriculum Learning for Domain Adaptation in Neural Machine Translationcited by 59
  3. 2018An Empirical Exploration of Curriculum Learning for Neural Machine Translationcited by 58
  4. 2019compare-mt: A Tool for Holistic Comparison of Language Generation Systemscited by 43
  5. 2017Dynamic Data Selection for Neural Machine Translationcited by 33
  6. 2020Meta-Learning for Few-Shot NMT Adaptationcited by 20
  7. 2019MetaMT,a MetaLearning Method Leveraging Multiple Domain Data for Low Resource Machine Translationcited by 17
  8. 2017Cynical Selection of Language Model Training Datacited by 13
  9. 2019Shared-Private Bilingual Word Embeddings for Neural Machine Translationcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 6; 2023: 7; 2024: 6; 2025: 0; 2026: 1.

28 papers.

Sort:

By area:

  1. 2022Efficient Methods for Natural Language Processing: A Surveycited by 78
  2. 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
  3. 2023A Review of Deep Learning for Video Captioningcited by 28
  4. 2021Progressive Multi-Granularity Training for Non-Autoregressive Translationcited by 25
  5. 2021Improving Neural Machine Translation by Bidirectional Trainingcited by 17
  6. 2024Boost Your Human Image Generation Model via Direct Preference Optimizationcited by 16
  7. 2021On the Complementarity between Pre-Training and Back-Translation for Neural Machine Translationcited by 14
  8. 2022Efficient Pre-training of Masked Language Model via Concept-based Curriculum Maskingcited by 12
  9. 2021Improving Both Domain Robustness and Domain Adaptability in Machine Translationcited by 11
  10. 2022Data Selection Curriculum for Neural Machine Translationcited by 11
  11. 2024Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuningcited by 11
  12. 2021Self-Guided Curriculum Learning for Neural Machine Translationcited by 9
16 more
  1. 2021Difficulty-Aware Machine Translation Evaluationcited by 6
  2. 2024A Psychology-based Unified Dynamic Framework for Curriculum Learningcited by 6
  3. 2024MELT: Materials-aware Continued Pre-training for Language Model Adaptation to Materials Sciencecited by 5
  4. 2022ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translationcited by 4
  5. 2023Cold-start Bundle Recommendation via Popularity-based Coalescence and Curriculum Heatingcited by 4
  6. 2024HOP to the Next Tasks and Domains for Continual Learning in NLPcited by 3
  7. 2022DaLC: Domain Adaptation Learning Curve Prediction for Neural Machine Translationcited by 2
  8. 2022m4Adapter: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adaptercited by 2
  9. 2023Curriculum Guided Domain Adaptation in the Darkcited by 2
  10. 2023BIOptimus: Pre-training an Optimal Biomedical Language Model with Curriculum Learning for Named Entity Recognitioncited by 2
  11. 2023Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrixcited by 2
  12. 2024A Two-Stage Prediction-Aware Contrastive Learning Framework for Multi-Intent NLUcited by 2
  13. 2023ERNetCL: A novel emotion recognition network in textual conversation based on curriculum learning strategycited by 1
  14. 2026CLewR: Curriculum Learning with Restarts for Machine Translation Preference Learningcited by 1
  15. 2021Reinforcement Learning for Few-Shot Text Generation Adaptationcited by 0
  16. 2023Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translationcited by 0