mlsanityData to 7 Oct 2026

Adapting High-resource NMT Models to Translate Low-resource Related Languages without Parallel Data

arXiv 2105.15071 ↗First posted 31 May 2021cs.CLcited by 17

Not on the map. Why?

Abstract (arXiv)

The scarcity of parallel data is a major obstacle for training high-quality machine translation systems for low-resource languages. Fortunately, some low-resource languages are linguistically related or similar to high-resource languages; these related languages may share many lexical or syntactic structures. In this work, we exploit this linguistic overlap to facilitate translating to and from a low-resource language with only monolingual data, in addition to any parallel data in the related high-resource language. Our method, NMT-Adapt, combines denoising autoencoding, back-translation and adversarial objectives to utilize monolingual data for low-resource adaptation. We experiment on 7 languages from three different language families and show that our technique significantly improves translation into low-resource language compared to other translation baselines.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 36 of its 47 references that are in the map. First posted on arXiv 31 May 2021.

Builds on

36 of 47 references.

References · 36

  1. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  2. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  5. 2019Cross-lingual Language Model Pretrainingcited by 1,088
  6. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  7. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  8. 2020Beyond English-Centric Multilingual Machine Translationcited by 559
  9. 2019CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Datacited by 544
  10. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
  11. 2019MASS: Masked Sequence to Sequence Pre-training for Language Generationcited by 345
  12. 2017Unsupervised Machine Translation Using Monolingual Corpora Onlycited by 272
24 more
  1. 2019CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEBcited by 177
  2. 2017Unsupervised Neural Machine Translationcited by 148
  3. 2018Phrase-Based & Neural Unsupervised Machine Translationcited by 138
  4. 2019CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairscited by 136
  5. 2018When and Why are Pre-trained Word Embeddings Useful for Neural Machine Translation?cited by 125
  6. 2020KUISAIL at SemEval-2020 Task 12: BERT-CNN for Offensive Speech Identification in Social Mediacited by 84
  7. 2018Rapid Adaptation of Neural Machine Translation to New Languagescited by 82
  8. 2017The IIT Bombay English-Hindi Parallel Corpuscited by 74
  9. 2020TICO-19: the Translation Initiative for Covid-19cited by 67
  10. 2019Improved Zero-shot Neural Machine Translation via Ignoring Spurious Correlationscited by 61
  11. 2019The Missing Ingredient in Zero-Shot Neural Machine Translationcited by 59
  12. 2020Cross-lingual Retrieval for Iterative Self-Supervised Trainingcited by 54
  13. 2019Generalized Data Augmentation for Low-Resource Translationcited by 53
  14. 2020Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translationcited by 51
  15. 2018DialogWAE: Multimodal Response Generation with Conditional Wasserstein Auto-Encodercited by 44
  16. 2018Automatic Language Identification in Texts: A Surveycited by 40
  17. 2020A Multilingual View of Unsupervised Machine Translationcited by 23
  18. 2017A Teacher-Student Framework for Zero-Resource Neural Machine Translationcited by 22
  19. 2019Consistency by Agreement in Zero-shot Neural Machine Translationcited by 22
  20. 2020Harnessing Multilinguality in Unsupervised Machine Translation for Rare Languagescited by 22
  21. 2019Adapting Multilingual Neural Machine Translation to Unseen Languagescited by 12
  22. 2020Reference Language based Unsupervised Neural Machine Translationcited by 12
  23. 2018Neural Machine Translation into Language Varietiescited by 9
  24. 2019Unsupervised Neural Dialect Translation with Commonality and Diversity Modelingcited by 5

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 4; 2023: 4; 2024: 3; 2025: 2.

17 papers.

Sort:

By area:

  1. 2022A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translationcited by 97
  2. 2021Survey of Low-Resource Machine Translationcited by 92
  3. 2022SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languagescited by 16
  4. 2021Don't Go Far Off: An Empirical Study on Neural Poetry Translationcited by 15
  5. 2025Scaling Low-Resource MT via Synthetic Data Generation with LLMscited by 14
  6. 2024The Zeno's Paradox of `Low-Resource' Languagescited by 12
  7. 2025Understanding In-Context Machine Translation for Low-Resource Languages: A Case Study on Manchucited by 12
  8. 2021Towards Making the Most of Multilingual Pretraining for Zero-Shot Neural Machine Translationcited by 8
  9. 2022Continual Learning of Neural Machine Translation within Low Forgetting Risk Regionscited by 6
  10. 2023Letz Translate: Low-Resource Machine Translation for Luxembourgishcited by 5
  11. 2023Neural Machine Translation Data Generation and Augmentation using ChatGPTcited by 5
  12. 2024A Tulu Resource for Machine Translationcited by 4
5 more
  1. 2022Multilingual Bidirectional Unsupervised Translation Through Multilingual Finetuning and Back-Translationcited by 3
  2. 2023Extending Multilingual Machine Translation through Imitation Learningcited by 3
  3. 2023Exploiting Multilingualism in Low-resource Neural Machine Translation via Adversarial Learningcited by 1
  4. 2021Classification-based Quality Estimation: Small and Efficient Models for Real-world Applicationscited by 0
  5. 2024Deterministic Reversible Data Augmentation for Neural Machine Translationcited by 0