# Meta-Learning for Few-Shot NMT Adaptation

arXiv: https://arxiv.org/abs/2004.02745 · HTML: https://mlsanity.com/paper/2004.02745/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2020.

## Built on by (most cited first, 20 of 20)

- [FLEX: Unifying Evaluation for Few-Shot NLP](https://mlsanity.com/paper/2107.07170/) (2021)
- [Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Survey](https://mlsanity.com/paper/2104.06951/) (2021)
- [Exploiting Adapters for Cross-lingual Low-resource Speech Recognition](https://mlsanity.com/paper/2105.11905/) (2021)
- [Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation](https://mlsanity.com/paper/2103.02262/) (2021)
- [Meta-learning approaches for few-shot learning: A survey of recent advances](https://mlsanity.com/paper/2303.07502/) (2023)
- [Contrastive Learning for Prompt-Based Few-Shot Language Learners](https://mlsanity.com/paper/2205.01308/) (2022)
- [Few-shot learning for medical text: A systematic review](https://mlsanity.com/paper/2204.14081/) (2022)
- [Improving Both Domain Robustness and Domain Adaptability in Machine Translation](https://mlsanity.com/paper/2112.08288/) (2021)
- [Meta-learning in healthcare: A survey](https://mlsanity.com/paper/2308.02877/) (2023)
- [Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation](https://mlsanity.com/paper/2203.11670/) (2022)
- [MetaAdapt: Domain Adaptive Few-Shot Misinformation Detection via Meta Learning](https://mlsanity.com/paper/2305.12692/) (2023)
- [Embedding Hallucination for Few-Shot Language Fine-tuning](https://mlsanity.com/paper/2205.01307/) (2022)
- [Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2310.16959/) (2023)
- [Cross-Modal Augmentation for Few-Shot Multimodal Fake News Detection](https://mlsanity.com/paper/2407.12880/) (2024)
- [m4Adapter: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter](https://mlsanity.com/paper/2210.11912/) (2022)
- [Domain adapted machine translation: What does catastrophic forgetting forget and why?](https://mlsanity.com/paper/2412.17537/) (2024)
- [Few-Shot Domain Adaptation for Grammatical Error Correction via Meta-Learning](https://mlsanity.com/paper/2101.12409/) (2021)
- [Data Augmentation for Machine Translation via Dependency Subtree Swapping](https://mlsanity.com/paper/2307.07025/) (2023)
- [Additive Interventions Yield Robust Multi-Domain Machine Translation Models](https://mlsanity.com/paper/2210.12727/) (2022)
- [Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translation](https://mlsanity.com/paper/2309.02640/) (2023)

## 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).