mlsanityData to 7 Oct 2026

Survey of Low-Resource Machine Translation

arXiv 2109.00486 ↗First posted 1 Sep 2021cs.CLcited by 92

Not on the map. Why?

Abstract (arXiv)

We present a survey covering the state of the art in low-resource machine translation research. There are currently around 7000 languages spoken in the world and almost all language pairs lack significant resources for training machine translation models. There has been increasing interest in research addressing the challenge of producing useful translation models when very little translated training data is available. We present a summary of this topical research field and provide a description of the techniques evaluated by researchers in several recent shared tasks in low-resource MT.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). Builds on 171 of its 314 references that are in the map. First posted on arXiv 1 Sep 2021.

Builds on

171 of 314 references.

References · 171

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  5. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  7. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  8. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  9. 2013Auto-Encoding Variational Bayescited by 3,980
  10. 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
  11. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  12. 2018Deep contextualized word representationscited by 2,285
38 more
  1. 2016Matching Networks for One Shot Learningcited by 2,246
  2. 2015Variational Inference with Normalizing Flowscited by 2,161
  3. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  4. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  5. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  6. 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,601
  7. 2016Enriching Word Vectors with Subword Informationcited by 1,578
  8. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  9. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,196
  10. 2019Cross-lingual Language Model Pretrainingcited by 1,088
  11. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  12. 2020COMET: A Neural Framework for MT Evaluationcited by 1,024
  13. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  14. 2015Scheduled Sampling for Sequence Prediction with Recurrent Neural Networkscited by 779
  15. 2016Sequence-Level Knowledge Distillationcited by 761
  16. 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 711
  17. 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 632
  18. 2020Language-agnostic BERT Sentence Embeddingcited by 621
  19. 2015Generating Sentences from a Continuous Spacecited by 607
  20. 2017Learning Sparse Neural Networks through L0 Regularizationcited by 571
  21. 2015Sequence Level Training with Recurrent Neural Networkscited by 568
  22. 2020Beyond English-Centric Multilingual Machine Translationcited by 559
  23. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 556
  24. 2017Word Translation Without Parallel Datacited by 480
  25. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
  26. 2018Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyondcited by 434
  27. 2019Unmasking Clever Hans Predictors and Assessing What Machines Really Learncited by 359
  28. 2019MASS: Masked Sequence to Sequence Pre-training for Language Generationcited by 345
  29. 2017Six Challenges for Neural Machine Translationcited by 334
  30. 2021Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translationcited by 333
  31. 2020Multilingual Translation with Extensible Multilingual Pretraining and Finetuningcited by 287
  32. 2020Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translationcited by 277
  33. 2017Unsupervised Machine Translation Using Monolingual Corpora Onlycited by 272
  34. 2019Compositionality decomposed: how do neural networks generalise?cited by 264
  35. 2019Massively Multilingual Neural Machine Translation in the Wild: Findings and Challengescited by 253
  36. 2017OpenNMT: Open-source Toolkit for Neural Machine Translationcited by 251
  37. 2019Massively Multilingual Neural Machine Translationcited by 246
  38. 2021Quality at a Glance: An Audit of Web-Crawled Multilingual Datasetscited by 241

50 most cited of 171 All 171 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 16; 2023: 11; 2024: 25; 2025: 24; 2026: 15.

92 papers.

Sort:

By area:

  1. 2022A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translationcited by 97
  2. 2024LLMs are Good Sign Language Translatorscited by 76
  3. 2024(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Textscited by 49
  4. 2022On the Blind Spots of Model-Based Evaluation Metrics for Text Generationcited by 48
  5. 2023XTREME-UP: A User-Centric Scarce-Data Benchmark for Under-Represented Languagescited by 34
  6. 2023A Paradigm Shift: The Future of Machine Translation Lies with Large Language Modelscited by 19
  7. 2022SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languagescited by 16
  8. 2024MORL-Prompt: An Empirical Analysis of Multi-Objective Reinforcement Learning for Discrete Prompt Optimizationcited by 16
  9. 2025Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Aheadcited by 15
  10. 2024On Subjective Uncertainty Quantification and Calibration in Natural Language Generationcited by 14
  11. 2025Scaling Low-Resource MT via Synthetic Data Generation with LLMscited by 14
  12. 2024Lexically Grounded Subword Segmentationcited by 13
38 more
  1. 2022Domain-Specific Text Generation for Machine Translationcited by 12
  2. 2024Low-Resource Machine Translation through Retrieval-Augmented LLM Prompting: A Study on the Mambai Languagecited by 12
  3. 2025Understanding In-Context Machine Translation for Low-Resource Languages: A Case Study on Manchucited by 12
  4. 2023PAXQA: Generating Cross-lingual Question Answering Examples at Training Scalecited by 10
  5. 2022Low-Resource Authorship Style Transfer: Can Non-Famous Authors Be Imitated?cited by 9
  6. 2024Leveraging Synthetic Audio Data for End-to-End Low-Resource Speech Translationcited by 9
  7. 2025Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translationcited by 8
  8. 2023On the Pareto Front of Multilingual Neural Machine Translationcited by 7
  9. 2023Neural Machine Translation for the Indigenous Languages of the Americas: An Introductioncited by 7
  10. 2022Improving Multilingual Neural Machine Translation System for Indic Languagescited by 6
  11. 2022Separating Grains from the Chaff: Using Data Filtering to Improve Multilingual Translation for Low-Resourced African Languagescited by 6
  12. 2023PuoBERTa: Training and evaluation of a curated language model for Setswanacited by 6
  13. 2022Geographical Distance Is The New Hyperparameter: A Case Study Of Finding The Optimal Pre-trained Language For English-isiZulu Machine Translationcited by 5
  14. 2022Exploring Diversity in Back Translation for Low-Resource Machine Translationcited by 5
  15. 2024No Train but Gain: Language Arithmetic for training-free Language Adapters enhancementcited by 5
  16. 2024A Systematic Review of NLP for Ghanaian Languages: Datasets, Models, and a Research Roadmapcited by 5
  17. 2024Rule-Based, Neural and LLM Back-Translation: Comparative Insights from a Variant of Ladincited by 5
  18. 2024Low-resource Machine Translation: what for? who for? An observational study on a dedicated Tetun language translation servicecited by 5
  19. 2025Evaluating Large Language Models for Cross-Lingual Retrievalcited by 5
  20. 2022Improving Neural Machine Translation of Indigenous Languages with Multilingual Transfer Learningcited by 4
  21. 2022Learning to translate by learning to communicatecited by 4
  22. 2023Enhancing Translation for Indigenous Languages: Experiments with Multilingual Modelscited by 4
  23. 2023Sheffield's Submission to the AmericasNLP Shared Task on Machine Translation into Indigenous Languagescited by 4
  24. 2025Connecting the Persian-speaking World through Transliterationcited by 4
  25. 2025Parallel Corpora for Machine Translation in Low-resource Indic Languages: A Comprehensive Reviewcited by 4
  26. 2021BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine Translationcited by 3
  27. 2023Decomposed Prompting for Machine Translation Between Related Languages using Large Language Modelscited by 3
  28. 2023Textless Speech-to-Speech Translation With Limited Parallel Datacited by 3
  29. 2024UMBCLU at SemEval-2024 Task 1A and 1C: Semantic Textual Relatedness with and without machine translationcited by 3
  30. 2025Found in Translation: Measuring Multilingual LLM Consistency as Simple as Translate then Evaluatecited by 3
  31. 2026Do LLM hallucination detectors suffer from low-resource effect?cited by 3
  32. 2022Cost-Effective Training in Low-Resource Neural Machine Translationcited by 2
  33. 2024The Impact of Syntactic and Semantic Proximity on Machine Translation with Back-Translationcited by 2
  34. 2024Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-resource Language Translationcited by 2
  35. 2025Limitations of Religious Data and the Importance of the Target Domain: Towards Machine Translation for Guinea-Bissau Creolecited by 2
  36. 2025Bangla-Bayanno: A 52K-Pair Bengali Visual Question Answering Dataset with LLM-Assisted Translation Refinementcited by 2
  37. 2026Improving Low-Resource Machine Translation via Round-Trip Reinforcement Learningcited by 2
  38. 2026SAGE: Sustainable Agent-Guided Expert-tuning for Culturally Attuned Translation in Low-Resource Southeast Asiacited by 2

50 most cited of 92 All 92 (JSON)