mlsanityData to 7 Oct 2026

Meta-Learning for Few-Shot NMT Adaptation

arXiv 2004.02745 ↗First posted 6 Apr 2020cs.CLcited by 20

Not on the map. Why?

Abstract (arXiv)

We present META-MT, a meta-learning approach to adapt Neural Machine Translation (NMT) systems in a few-shot setting. META-MT provides a new approach to make NMT models easily adaptable to many target domains with the minimal amount of in-domain data. We frame the adaptation of NMT systems as a meta-learning problem, where we learn to adapt to new unseen domains based on simulated offline meta-training domain adaptation tasks. We evaluate the proposed meta-learning strategy on ten domains with general large scale NMT systems. We show that META-MT significantly outperforms classical domain adaptation when very few in-domain examples are available. Our experiments shows that META-MT can outperform classical fine-tuning by up to 2.5 BLEU points after seeing only 4, 000 translated words (300 parallel sentences).

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 6; 2022: 6; 2023: 6; 2024: 2.

20 papers.

Sort:

  1. 2021FLEX: Unifying Evaluation for Few-Shot NLPcited by 67
  2. 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
  3. 2021Exploiting Adapters for Cross-lingual Low-resource Speech Recognitioncited by 33
  4. 2021Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translationcited by 28
  5. 2023Meta-learning approaches for few-shot learning: A survey of recent advancescited by 25
  6. 2022Contrastive Learning for Prompt-Based Few-Shot Language Learnerscited by 17
  7. 2022Few-shot learning for medical text: A systematic reviewcited by 12
  8. 2021Improving Both Domain Robustness and Domain Adaptability in Machine Translationcited by 11
  9. 2023Meta-learning in healthcare: A surveycited by 9
  10. 2022Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitationcited by 8
  11. 2023MetaAdapt: Domain Adaptive Few-Shot Misinformation Detection via Meta Learningcited by 8
  12. 2022Embedding Hallucination for Few-Shot Language Fine-tuningcited by 5
8 more
  1. 2023Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuningcited by 4
  2. 2024Cross-Modal Augmentation for Few-Shot Multimodal Fake News Detectioncited by 3
  3. 2022m4Adapter: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adaptercited by 2
  4. 2024Domain adapted machine translation: What does catastrophic forgetting forget and why?cited by 2
  5. 2021Few-Shot Domain Adaptation for Grammatical Error Correction via Meta-Learningcited by 1
  6. 2023Data Augmentation for Machine Translation via Dependency Subtree Swappingcited by 1
  7. 2022Additive Interventions Yield Robust Multi-Domain Machine Translation Modelscited by 0
  8. 2023Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translationcited by 0