mlsanityData to 7 Oct 2026

Improving Both Domain Robustness and Domain Adaptability in Machine Translation

arXiv 2112.08288 ↗First posted 15 Dec 2021cs.CLcited by 11

Not on the map. Why?

Abstract (arXiv)

We consider two problems of NMT domain adaptation using meta-learning. First, we want to reach domain robustness, i.e., we want to reach high quality on both domains seen in the training data and unseen domains. Second, we want our systems to be adaptive, i.e., making it possible to finetune systems with just hundreds of in-domain parallel sentences. We study the domain adaptability of meta-learning when improving the domain robustness of the model. In this paper, we propose a novel approach, RMLNMT (Robust Meta-Learning Framework for Neural Machine Translation Domain Adaptation), which improves the robustness of existing meta-learning models. More specifically, we show how to use a domain classifier in curriculum learning and we integrate the word-level domain mixing model into the meta-learning framework with a balanced sampling strategy. Experiments on EnglishrightarrowGerman and EnglishrightarrowChinese translation show that RMLNMT improves in terms of both domain robustness and domain adaptability in seen and unseen domains. Our source code is available at https://github.com/lavine-lmu/RMLNMT.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 32 of its 56 references that are in the map. First posted on arXiv 15 Dec 2021.

Builds on

32 of 56 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  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. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  6. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  7. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  8. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
  9. 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
  10. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  11. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
  12. 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 632
20 more
  1. 2020Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metricscited by 155
  2. 2018Meta-Learning for Low-Resource Neural Machine Translationcited by 105
  3. 2018A Survey of Domain Adaptation for Neural Machine Translationcited by 64
  4. 2019Domain Robustness in Neural Machine Translationcited by 64
  5. 2019Curriculum Learning for Domain Adaptation in Neural Machine Translationcited by 59
  6. 2020Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Taskscited by 51
  7. 2019Investigating Meta-Learning Algorithms for Low-Resource Natural Language Understanding Taskscited by 48
  8. 2020Meta-learning for Few-shot Natural Language Processing: A Surveycited by 42
  9. 2019Domain Adaptive Dialog Generation via Meta Learningcited by 41
  10. 2019Simple and Effective Noisy Channel Modeling for Neural Machine Translationcited by 37
  11. 2016Domain Control for Neural Machine Translationcited by 36
  12. 2019Domain Adaptation of Neural Machine Translation by Lexicon Inductioncited by 33
  13. 2016Neural Machine Translation with Reconstructioncited by 28
  14. 2016Fast Domain Adaptation for Neural Machine Translationcited by 28
  15. 2021Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translationcited by 28
  16. 2020Meta-Learning for Few-Shot NMT Adaptationcited by 20
  17. 2019MetaMT,a MetaLearning Method Leveraging Multiple Domain Data for Low Resource Machine Translationcited by 17
  18. 2019Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixingcited by 14
  19. 2021Meta-Learning with Variational Semantic Memory for Word Sense Disambiguationcited by 2
  20. 2019Word-based Domain Adaptation for Neural Machine Translationcited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 5; 2025: 2.

11 papers.

  1. 2024LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedbackcited by 51
  2. 2024Style-Specific Neurons for Steering LLMs in Text Style Transfercited by 24
  3. 2024Large Language Model for Multi-Domain Translation: Benchmarking and Domain CoT Fine-tuningcited by 11
  4. 2024Whose wife is it anyway? Assessing bias against same-gender relationships in machine translationcited by 6
  5. 2025From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corporacited by 6
  6. 2023Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translationcited by 5
  7. 2023Extending Multilingual Machine Translation through Imitation Learningcited by 3
  8. 2025DMDTEval: An Evaluation and Analysis of LLMs on Disambiguation in Multi-domain Translationcited by 3
  9. 2022m4Adapter: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adaptercited by 2
  10. 2023Epi-Curriculum: Episodic Curriculum Learning for Low-Resource Domain Adaptation in Neural Machine Translationcited by 0
  11. 2024An Empirical Study on the Robustness of Massively Multilingual Neural Machine Translationcited by 0