mlsanityData to 7 Oct 2026

Trivial Transfer Learning for Low-Resource Neural Machine Translation

arXiv 1809.00357 ↗First posted 2 Sep 2018cs.CLcited by 47

Not on the map. Why?

Abstract (arXiv)

Transfer learning has been proven as an effective technique for neural machine translation under low-resource conditions. Existing methods require a common target language, language relatedness, or specific training tricks and regimes. We present a simple transfer learning method, where we first train a "parent" model for a high-resource language pair and then continue the training on a lowresource pair only by replacing the training corpus. This "child" model performs significantly better than the baseline trained for lowresource pair only. We are the first to show this for targeting different languages, and we observe the improvements even for unrelated languages with different alphabets.

Key facts. Cited by 47 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 23; 2022: 6; 2023: 6; 2024: 6; 2025: 1; 2026: 5.

47 papers.

Sort:

  1. 2021Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languagescited by 133
  2. 2021Neural Machine Translation for Low-Resource Languages: A Surveycited by 108
  3. 2021Survey of Low-Resource Machine Translationcited by 92
  4. 2021Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translationcited by 74
  5. 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
  6. 2021Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translationcited by 29
  7. 2021EmailSum: Abstractive Email Thread Summarizationcited by 24
  8. 2021A Survey on Low-Resource Neural Machine Translationcited by 16
  9. 2023Viewing Knowledge Transfer in Multilingual Machine Translation Through a Representational Lenscited by 15
  10. 2021Bridging Subword Gaps in Pretrain-Finetune Paradigm for Natural Language Generationcited by 14
  11. 2022On the Generalization for Transfer Learning: An Information-Theoretic Analysiscited by 11
  12. 2021IndT5: A Text-to-Text Transformer for 10 Indigenous Languagescited by 10
35 more
  1. 2021Rethinking Data Augmentation for Low-Resource Neural Machine Translation: A Multi-Task Learning Approachcited by 8
  2. 2021Extremely low-resource machine translation for closely related languagescited by 7
  3. 2023Order Matters in the Presence of Dataset Imbalance for Multilingual Learningcited by 7
  4. 2021English2Gbe: A multilingual machine translation model for {Fon/Ewe}Gbecited by 5
  5. 2024Investigating Neural Machine Translation for Low-Resource Languages: Using Bavarian as a Case Studycited by 5
  6. 2021Token-wise Curriculum Learning for Neural Machine Translationcited by 4
  7. 2021AUGVIC: Exploiting BiText Vicinity for Low-Resource NMTcited by 4
  8. 2022Improving Neural Machine Translation of Indigenous Languages with Multilingual Transfer Learningcited by 4
  9. 2022ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translationcited by 4
  10. 2023Parallel Corpus for Indigenous Language Translation: Spanish-Mazatec and Spanish-Mixteccited by 4
  11. 2021Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languagescited by 3
  12. 2021Cross-lingual Transferring of Pre-trained Contextualized Language Modelscited by 3
  13. 2021HintedBT: Augmenting Back-Translation with Quality and Transliteration Hintscited by 3
  14. 2022Sub-Word Alignment Is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translationcited by 3
  15. 2023Multilingual k-Nearest-Neighbor Machine Translationcited by 3
  16. 2021EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMTcited by 2
  17. 2024Disentangling the Roles of Target-Side Transfer and Regularization in Multilingual Machine Translationcited by 2
  18. 2024Improving Low-Resource Machine Translation via Cross-Linguistic Transfer from Typologically Similar High-Resource Languagescited by 2
  19. 2026KD4MT: A Survey of Knowledge Distillation for Machine Translationcited by 2
  20. 2021Self-Learning for Zero Shot Neural Machine Translationcited by 1
  21. 2021Machine Translation of Low-Resource Indo-European Languagescited by 1
  22. 2023Improving Polish to English Neural Machine Translation with Transfer Learning: Effects of Data Volume and Language Similaritycited by 1
  23. 2023Data Augmentation for Machine Translation via Dependency Subtree Swappingcited by 1
  24. 2021Zero-Shot Language Transfer vs Iterative Back Translation for Unsupervised Machine Translationcited by 0
  25. 2021Coarse-To-Fine And Cross-Lingual ASR Transfercited by 0
  26. 2022Cross-lingual Transfer Learning for Fake News Detector in a Low-Resource Languagecited by 0
  27. 2022Findings of the Covid-19 MLIA Machine Translation Taskcited by 0
  28. 2024Non-Fluent Synthetic Target-Language Data Improve Neural Machine Translationcited by 0
  29. 2024ChakmaNMT: Machine Translation for a Low-Resource and Endangered Language via Transliterationcited by 0
  30. 2024Quantity vs. Quality of Monolingual Source Data in Automatic Text Translation: Can It Be Too Little If It Is Too Good?cited by 0
  31. 2025Low-Resource English-Tigrinya MT: Leveraging Multilingual Models, Custom Tokenizers, and Clean Evaluation Benchmarkscited by 0
  32. 2026Leveraging Sentence-oriented Augmentation and Transformer-Based Architecture for Vietnamese-Bahnaric Translationcited by 0
  33. 2026The Impact of Vocabulary Overlaps on Knowledge Transfer in Multilingual Machine Translationcited by 0
  34. 2026Cross-Lingual Transfer for Machine Translation in Turkic Languagescited by 0
  35. 2026Instability of LLM Pre-Pretraining: It Doesn't Always Help. An Investigation on Multiple Languagescited by 0