Neural Machine Translation for Low-Resource Languages: A Survey
Not on the map. Why?
Abstract (arXiv)
Neural Machine Translation (NMT) has seen a tremendous spurt of growth in less than ten years, and has already entered a mature phase. While considered as the most widely used solution for Machine Translation, its performance on low-resource language pairs still remains sub-optimal compared to the high-resource counterparts, due to the unavailability of large parallel corpora. Therefore, the implementation of NMT techniques for low-resource language pairs has been receiving the spotlight in the recent NMT research arena, thus leading to a substantial amount of research reported on this topic. This paper presents a detailed survey of research advancements in low-resource language NMT (LRL-NMT), along with a quantitative analysis aimed at identifying the most popular solutions. Based on our findings from reviewing previous work, this survey paper provides a set of guidelines to select the possible NMT technique for a given LRL data setting. It also presents a holistic view of the LRL-NMT research landscape and provides a list of recommendations to further enhance the research efforts on LRL-NMT.
Key facts. Cited by 108 papers in the map (data through 7 Oct 2026). Builds on 143 of its 226 references that are in the map. First posted on arXiv 29 Jun 2021.
Builds on
143 of 226 references.
References · 143
- 2017Attention Is All You Needcited by 59,932
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,907
- 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
- 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,303
- 2019Cross-lingual Language Model Pretrainingcited by 1,088
- 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
- 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 951
- 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 789
- 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
- 2020XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalizationcited by 738
38 more
- 2020Language-agnostic BERT Sentence Embeddingcited by 621
- 2020Beyond English-Centric Multilingual Machine Translationcited by 559
- 2017Word Translation Without Parallel Datacited by 480
- 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
- 2019MASS: Masked Sequence to Sequence Pre-training for Language Generationcited by 345
- 2017Six Challenges for Neural Machine Translationcited by 334
- 2020Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translationcited by 277
- 2017Unsupervised Machine Translation Using Monolingual Corpora Onlycited by 272
- 2019Massively Multilingual Neural Machine Translation in the Wild: Findings and Challengescited by 253
- 2017OpenNMT: Open-source Toolkit for Neural Machine Translationcited by 251
- 2019Evaluating Gender Bias in Machine Translationcited by 247
- 2019Massively Multilingual Neural Machine Translationcited by 246
- 2021Quality at a Glance: An Audit of Web-Crawled Multilingual Datasetscited by 241
- 2019WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipediacited by 221
- 2018Marian: Fast Neural Machine Translation in C++cited by 202
- 2016Transfer Learning for Low-Resource Neural Machine Translationcited by 188
- 2019CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEBcited by 177
- 2020A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarioscited by 170
- 2020Participatory Research for Low-resourced Machine Translation: A Case Study in African Languagescited by 159
- 2015On Using Monolingual Corpora in Neural Machine Translationcited by 149
- 2017Unsupervised Neural Machine Translationcited by 148
- 2016Dual Learning for Machine Translationcited by 146
- 2019Choosing Transfer Languages for Cross-Lingual Learningcited by 143
- 2017Data Augmentation for Low-Resource Neural Machine Translationcited by 139
- 2018Phrase-Based & Neural Unsupervised Machine Translationcited by 138
- 2018When and Why are Pre-trained Word Embeddings Useful for Neural Machine Translation?cited by 125
- 2020UnQovering Stereotyping Biases via Underspecified Questionscited by 124
- 2016Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanismcited by 117
- 2018Meta-Learning for Low-Resource Neural Machine Translationcited by 105
- 2019Neural Machine Translation: A Review and Surveycited by 99
- 2019Multilingual Neural Machine Translation with Knowledge Distillationcited by 95
- 2020Low-resource Languages: A Review of Past Work and Future Challengescited by 90
- 2018Tensor2Tensor for Neural Machine Translationcited by 85
- 2018Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddingscited by 83
- 2018Rapid Adaptation of Neural Machine Translation to New Languagescited by 82
- 2016Toward Multilingual Neural Machine Translation with Universal Encoder and Decodercited by 76
- 2019Tagged Back-Translationcited by 76
- 2020The Radicalization Risks of GPT-3 and Advanced Neural Language Modelscited by 76
50 most cited of 143 All 143 (JSON)
Built on by
Citing papers per year: 2021: 5; 2022: 13; 2023: 21; 2024: 38; 2025: 18; 2026: 13.
108 papers.
Sort:
By area:
- 2023Language Model Tokenizers Introduce Unfairness Between Languagescited by 207
- 2023A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethicscited by 162
- 2023Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Modelscited by 144
- 2022Pretrained Language Models for Text Generation: A Surveycited by 121
- 2021Survey of Low-Resource Machine Translationcited by 92
- 2022Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP Worldcited by 55
- 2023Unveiling Security, Privacy, and Ethical Concerns of ChatGPTcited by 53
- 2023Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimescited by 52
- 2021Multilingual training for Software Engineeringcited by 43
- 2024The Future of Large Language Model Pre-training is Federatedcited by 30
- 2024Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Researchcited by 26
- 2022Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation?cited by 24
38 more
- 2023Beyond Static Datasets: A Deep Interaction Approach to LLM Evaluationcited by 24
- 2024Open Ko-LLM Leaderboard: Evaluating Large Language Models in Korean with Ko-H5 Benchmarkcited by 23
- 2025Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judgecited by 23
- 2023JWSign: A Highly Multilingual Corpus of Bible Translations for more Diversity in Sign Language Processingcited by 18
- 2022USCORE: An Effective Approach to Fully Unsupervised Evaluation Metrics for Machine Translationcited by 15
- 2024Quality Does Matter: A Detailed Look at the Quality and Utility of Web-Mined Parallel Corporacited by 13
- 2022Towards Better Chinese-centric Neural Machine Translation for Low-resource Languagescited by 11
- 2023Natural Language Processing in Ethiopian Languages: Current State, Challenges, and Opportunitiescited by 11
- 2023Large Human Language Models: A Need and the Challengescited by 11
- 2024Prompt Refinement with Image Pivot for Text-to-Image Generationcited by 11
- 2024FAIR Enough: How Can We Develop and Assess a FAIR-Compliant Dataset for Large Language Models' Training?cited by 9
- 2024Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitationcited by 9
- 2022Computational historical linguistics and language diversity in South Asiacited by 8
- 2024Brain-inspired Artificial Intelligence: A Comprehensive Reviewcited by 8
- 2023Neural Machine Translation for the Indigenous Languages of the Americas: An Introductioncited by 7
- 2023First Attempt at Building Parallel Corpora for Machine Translation of Northeast India's Very Low-Resource Languagescited by 7
- 2022A Theory of Unsupervised Translation Motivated by Understanding Animal Communicationcited by 6
- 2023An evaluation of Google Translate for Sanskrit to English translation via sentiment and semantic analysiscited by 6
- 2023Knowledge Relation Rank Enhanced Heterogeneous Learning Interaction Modeling for Neural Graph Forgetting Knowledge Tracingcited by 6
- 2023PuoBERTa: Training and evaluation of a curated language model for Setswanacited by 6
- 2024LLM-Assisted Rule Based Machine Translation for Low/No-Resource Languagescited by 6
- 2024Multistage Fine-tuning Strategies for Automatic Speech Recognition in Low-resource Languagescited by 6
- 2024Sinhala Transliteration: A Comparative Analysis Between Rule-based and Seq2Seq Approachescited by 6
- 2025Bhaasha, Bhasa, Zaban: A Survey for Low-Resourced Languages in South Asia -- Current Stage and Challengescited by 6
- 2021Training Cross-Lingual embeddings for Setswana and Sepedicited by 5
- 2023Low-Resourced Machine Translation for Senegalese Wolof Languagecited by 5
- 2023Leveraging Auxiliary Domain Parallel Data in Intermediate Task Fine-tuning for Low-resource Translationcited by 5
- 2024A Systematic Review of NLP for Ghanaian Languages: Datasets, Models, and a Research Roadmapcited by 5
- 2024Worldwide Federated Training of Language Modelscited by 5
- 2024On the Evaluation Practices in Multilingual NLP: Can Machine Translation Offer an Alternative to Human Translations?cited by 5
- 2024Rule-Based, Neural and LLM Back-Translation: Comparative Insights from a Variant of Ladincited by 5
- 2024Low-resource Machine Translation: what for? who for? An observational study on a dedicated Tetun language translation servicecited by 5
- 2025TLUE: A Tibetan Language Understanding Evaluation Benchmarkcited by 5
- 2022Improving Neural Machine Translation of Indigenous Languages with Multilingual Transfer Learningcited by 4
- 2023RoDia: A New Dataset for Romanian Dialect Identification from Speechcited by 4
- 2024Cross-Lingual Learning vs. Low-Resource Fine-Tuning: A Case Study with Fact-Checking in Turkishcited by 4
- 2024Representation Bias of Adolescents in AI: A Bilingual, Bicultural Studycited by 4
- 2021TinyDefectNet: Highly Compact Deep Neural Network Architecture for High-Throughput Manufacturing Visual Quality Inspectioncited by 3
50 most cited of 108 All 108 (JSON)
- 2026Precision over Scale: A Polish-Silesian Benchmark and a Translation System Outperforming Open-Source and Commercial Models1 Oct 2026
- 2026Evaluating Communicative Success in Machine-Translated Conversation17 Sep 2026
- 2026BM25-Augmented Many-Shot Translation for Low-Resource North-Eastern Indian Languages13 Aug 2026
- 2026BnBERT-iPET: Sparse Few-Shot Language Modeling for Bengali via Lottery Ticket Pruning5 Aug 2026
- 2026Echoes Across Vietnam's Highlands, Delta, and Coast: A Multilingual Corpus for Cham, Khmer, and Tay-Nung9 Jul 2026
- 2026VHDLSuite: Unified Pipeline for LLM VHDL Generation with Data Synthesis and Evaluation11 Jun 2026
- 2026Culturally-Adapted Red-Teaming Across East and Southeast Asian Contexts: A Methodological and Comparative Analysis8 Jun 2026
- 2026CRAFT: Clustered Regression for Adaptive Filtering of Training data24 Apr 2026
- 2026SAGE: Sustainable Agent-Guided Expert-tuning for Culturally Attuned Translation in Low-Resource Southeast Asia20 Mar 2026
- 2026Ensemble Self-Training for Unsupervised Machine Translation17 Mar 2026
- 2026Data Kernel Perspective Space Performance Guarantees for Synthetic Data from Transformer Models4 Feb 2026
- 2026LeanTutor: Towards a Verified AI Mathematical Proof Tutor24 Jan 2026
38 more
- 2026Context Volume Drives Performance: Tackling Domain Shift in Extremely Low-Resource Translation via RAG15 Jan 2026
- 2025Opportunities and Challenges of Natural Language Processing for Low-Resource Senegalese Languages in Social Science Research24 Dec 2025
- 2025OmniMER: Auxiliary-Enhanced LLM Adaptation for Indonesian Multimodal Emotion Recognition22 Dec 2025
- 2025Zero-Shot Performance Prediction for Probabilistic Scaling Laws19 Oct 2025
- 2025The African Languages Lab: A Collaborative Approach to Advancing Low-Resource African NLP7 Oct 2025
- 2025SiniticMTError: A Machine Translation Dataset with Error Annotations for Sinitic Languages24 Sep 2025
- 2025Bhaasha, Bhasa, Zaban: A Survey for Low-Resourced Languages in South Asia -- Current Stage and Challenges15 Sep 2025
- 2025Exploring NLP Benchmarks in an Extremely Low-Resource Setting4 Sep 2025
- 2025Bangla-Bayanno: A 52K-Pair Bengali Visual Question Answering Dataset with LLM-Assisted Translation Refinement27 Aug 2025
- 2025LeanTutor: Towards a Verified AI Mathematical Proof Tutor10 Jun 2025
- 2025An End-to-End Approach for Child Reading Assessment in the Xhosa Language23 May 2025
- 2025In-Domain African Languages Translation Using LLMs and Multi-armed Bandits21 May 2025
- 2025Enhancing Low-Resource Minority Language Translation with LLMs and Retrieval-Augmented Generation for Cultural Nuances16 May 2025
- 2025Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge10 Apr 2025
- 2025Beyond Vanilla Fine-Tuning: Leveraging Multistage, Multilingual, and Domain-Specific Methods for Low-Resource Machine Translation28 Mar 2025
- 2025An evaluation of LLMs and Google Translate for translation of selected Indian languages via sentiment and semantic analyses27 Mar 2025
- 2025TLUE: A Tibetan Language Understanding Evaluation Benchmark15 Mar 2025
- 2025AI Thinking as a Meaning-Centered Framework: Reimagining Language Technologies Through Community Agency19 Feb 2025
- 2025Beyond English: Evaluating Automated Measurement of Moral Foundations in Non-English Discourse with a Chinese Case Study4 Feb 2025
- 2024Sinhala Transliteration: A Comparative Analysis Between Rule-based and Seq2Seq Approaches31 Dec 2024
- 2024Exploiting Domain-Specific Parallel Data on Multilingual Language Models for Low-resource Language Translation27 Dec 2024
- 2024Towards Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)24 Dec 2024
- 2024Overview of the First Workshop on Language Models for Low-Resource Languages (LoResLM 2025)20 Dec 2024
- 2024NoLoR: An ASR-Based Framework for Expedited Endangered Language Documentation with Neo-Aramaic as a Case Study6 Dec 2024
- 2024From Priest to Doctor: Domain Adaptation for Low-Resource Neural Machine Translation1 Dec 2024
- 2024Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research30 Nov 2024
- 2024Low-resource Machine Translation: what for? who for? An observational study on a dedicated Tetun language translation service19 Nov 2024
- 2024VTechAGP: An Academic-to-General-Audience Text Paraphrase Dataset and Benchmark Models7 Nov 2024
- 2024Multistage Fine-tuning Strategies for Automatic Speech Recognition in Low-resource Languages7 Nov 2024
- 2024Leveraging Retrieval-Augmented Generation for Culturally Inclusive Hakka Chatbots: Design Insights and User Perceptions21 Oct 2024
- 2024Plug-and-Play Performance Estimation for LLM Services without Relying on Labeled Data10 Oct 2024
- 2024COMFORT: A Continual Fine-Tuning Framework for Foundation Models Targeted at Consumer Healthcare14 Sep 2024
- 2024Brain-inspired Artificial Intelligence: A Comprehensive Review27 Aug 2024
- 2024Generative-Adversarial Networks for Low-Resource Language Data Augmentation in Machine Translation24 Aug 2024
- 2024Representation Bias of Adolescents in AI: A Bilingual, Bicultural Study4 Aug 2024
- 2024Rule-Based, Neural and LLM Back-Translation: Comparative Insights from a Variant of Ladin11 Jul 2024
- 2024Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation11 Jul 2024
- 2024Enhancing Language Learning through Technology: Introducing a New English-Azerbaijani (Arabic Script) Parallel Corpus6 Jul 2024
50 newest of 108 All 108 (JSON)
- 2025Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judgecited by 23
- 2024Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitationcited by 9
- 2026Culturally-Adapted Red-Teaming Across East and Southeast Asian Contexts: A Methodological and Comparative Analysiscited by 0
- 2026Culturally-Adapted Red-Teaming Across East and Southeast Asian Contexts: A Methodological and Comparative Analysis8 Jun 2026
- 2025Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge10 Apr 2025
- 2024Are Large Language Models Really Bias-Free? Jailbreak Prompts for Assessing Adversarial Robustness to Bias Elicitation11 Jul 2024
- 2023Language Model Tokenizers Introduce Unfairness Between Languagescited by 207
- 2023A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethicscited by 162
- 2023Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Modelscited by 144
- 2022Pretrained Language Models for Text Generation: A Surveycited by 121
- 2021Survey of Low-Resource Machine Translationcited by 92
- 2022Some Languages are More Equal than Others: Probing Deeper into the Linguistic Disparity in the NLP Worldcited by 55
- 2023Unveiling Security, Privacy, and Ethical Concerns of ChatGPTcited by 53
- 2023Curated LLM: Synergy of LLMs and Data Curation for tabular augmentation in low-data regimescited by 52
- 2021Multilingual training for Software Engineeringcited by 43
- 2024The Future of Large Language Model Pre-training is Federatedcited by 30
- 2024Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Researchcited by 26
- 2022Pre-Trained Multilingual Sequence-to-Sequence Models: A Hope for Low-Resource Language Translation?cited by 24
12 most cited of 101 All 101 (JSON)
- 2026Precision over Scale: A Polish-Silesian Benchmark and a Translation System Outperforming Open-Source and Commercial Models1 Oct 2026
- 2026Evaluating Communicative Success in Machine-Translated Conversation17 Sep 2026
- 2026BM25-Augmented Many-Shot Translation for Low-Resource North-Eastern Indian Languages13 Aug 2026
- 2026BnBERT-iPET: Sparse Few-Shot Language Modeling for Bengali via Lottery Ticket Pruning5 Aug 2026
- 2026Echoes Across Vietnam's Highlands, Delta, and Coast: A Multilingual Corpus for Cham, Khmer, and Tay-Nung9 Jul 2026
- 2026VHDLSuite: Unified Pipeline for LLM VHDL Generation with Data Synthesis and Evaluation11 Jun 2026
- 2026CRAFT: Clustered Regression for Adaptive Filtering of Training data24 Apr 2026
- 2026Ensemble Self-Training for Unsupervised Machine Translation17 Mar 2026
- 2026LeanTutor: Towards a Verified AI Mathematical Proof Tutor24 Jan 2026
- 2026Context Volume Drives Performance: Tackling Domain Shift in Extremely Low-Resource Translation via RAG15 Jan 2026
- 2025Opportunities and Challenges of Natural Language Processing for Low-Resource Senegalese Languages in Social Science Research24 Dec 2025
- 2025OmniMER: Auxiliary-Enhanced LLM Adaptation for Indonesian Multimodal Emotion Recognition22 Dec 2025
12 newest of 101 All 101 (JSON)