Data to 14 Oct 2026

Massively Multilingual Neural Machine Translation

arXiv 1903.00089 ↗First posted 28 Feb 2019cs.CLcited by 246

Not on the map. Why?

Abstract (arXiv)

Multilingual neural machine translation (NMT) enables training a single model that supports translation from multiple source languages into multiple target languages. In this paper, we push the limits of multilingual NMT in terms of number of languages being used. We perform extensive experiments in training massively multilingual NMT models, translating up to 102 languages to and from English within a single model. We explore different setups for training such models and analyze the trade-offs between translation quality and various modeling decisions. We report results on the publicly available TED talks multilingual corpus where we show that massively multilingual many-to-many models are effective in low resource settings, outperforming the previous state-of-the-art while supporting up to 59 languages. Our experiments on a large-scale dataset with 102 languages to and from English and up to one million examples per direction also show promising results, surpassing strong bilingual baselines and encouraging future work on massively multilingual NMT.

Key facts. Cited by 246 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2020: 1; 2021: 77; 2022: 56; 2023: 56; 2024: 26; 2025: 18; 2026: 12.

246 papers.

Sort:

By area:

2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,631
2022A Generalist Agentcited by 808
2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 560
2024Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuningcited by 177
2021Meta-learning via Language Model In-context Tuningcited by 164
2021Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languagescited by 136
2023Hallucinations in Large Multilingual Translation Modelscited by 129
2021Neural Machine Translation for Low-Resource Languages: A Surveycited by 109
2021Contrastive Learning for Many-to-many Multilingual Neural Machine Translationcited by 108
2022A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translationcited by 98
2022State-of-the-art generalisation research in NLP: A taxonomy and reviewcited by 98
2021Learning Compact Metrics for MTcited by 93

38 more

2021Survey of Low-Resource Machine Translationcited by 92
2021X-FACT: A New Benchmark Dataset for Multilingual Fact Checkingcited by 91
2023A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Modelscited by 89
2023Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptationcited by 81
2022A Simple Multi-Modality Transfer Learning Baseline for Sign Language Translationcited by 80
2021Scalable and Efficient MoE Training for Multitask Multilingual Modelscited by 76
2023A Benchmark for Learning to Translate a New Language from One Grammar Bookcited by 75
2022Building Machine Translation Systems for the Next Thousand Languagescited by 69
2021Trankit: A Light-Weight Transformer-based Toolkit for Multilingual Natural Language Processingcited by 68
2023Multilingual Large Language Models Are Not (Yet) Code-Switcherscited by 65
2021UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-trainingcited by 64
2025PolyGuard: A Multilingual Safety Moderation Tool for 17 Languagescited by 59
2021Facebook AI WMT21 News Translation Task Submissioncited by 57
2023CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translationcited by 57
2023Benchmarking Machine Translation with Cultural Awarenesscited by 53
2021A Survey on Green Deep Learningcited by 52
2021Learning Language Specific Sub-network for Multilingual Machine Translationcited by 48
2021The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translationcited by 47
2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
2022mFACE: Multilingual Summarization with Factual Consistency Evaluationcited by 42
2021Counter-Interference Adapter for Multilingual Machine Translationcited by 40
2021IndicBART: A Pre-trained Model for Indic Natural Language Generationcited by 39
2021Fast Nearest Neighbor Machine Translationcited by 37
2022MoESys: A Distributed and Efficient Mixture-of-Experts Training and Inference System for Internet Servicescited by 37
2022Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Modelcited by 36
2024X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scalecited by 36
2023SLTUNET: A Simple Unified Model for Sign Language Translationcited by 35
2021Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Taskcited by 34
2023Quantifying the Dialect Gap and its Correlates Across Languagescited by 33
2021Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitutioncited by 31
2023LLMRec: Benchmarking Large Language Models on Recommendation Taskcited by 30
2021Zero-shot Cross-lingual Transfer of Neural Machine Translation with Multilingual Pretrained Encoderscited by 24
2021Importance-based Neuron Allocation for Multilingual Neural Machine Translationcited by 23
2022Causes and Cures for Interference in Multilingual Translationcited by 23
2021Multilingual Unsupervised Neural Machine Translation with Denoising Adapterscited by 22
2023Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfercited by 22
2021Multilingual Domain Adaptation for NMT: Decoupling Language and Domain Information with Adapterscited by 21
2022Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translationcited by 21

50 most cited of 246 All 246 (JSON)