Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism
Not on the map. Why?
Abstract (arXiv)
We propose multi-way, multilingual neural machine translation. The proposed approach enables a single neural translation model to translate between multiple languages, with a number of parameters that grows only linearly with the number of languages. This is made possible by having a single attention mechanism that is shared across all language pairs. We train the proposed multi-way, multilingual model on ten language pairs from WMT'15 simultaneously and observe clear performance improvements over models trained on only one language pair. In particular, we observe that the proposed model significantly improves the translation quality of low-resource language pairs.
Key facts. Cited by 117 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Jan 2016.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2020: 1; 2021: 45; 2022: 30; 2023: 25; 2024: 9; 2025: 5; 2026: 2.
117 papers.
Sort:
By area:
- 2020GShard: Scaling Giant Models with Conditional Computation and Automatic Shardingcited by 1,601
- 2021Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languagescited by 133
- 2021Neural Machine Translation for Low-Resource Languages: A Surveycited by 108
- 2022A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translationcited by 97
- 2021Survey of Low-Resource Machine Translationcited by 92
- 2023A Benchmark for Learning to Translate a New Language from One Grammar Bookcited by 74
- 2022Building Machine Translation Systems for the Next Thousand Languagescited by 69
- 2023Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOMcited by 58
- 2021Facebook AI WMT21 News Translation Task Submissioncited by 57
- 2021A Survey on Green Deep Learningcited by 52
- 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
- 2021Learning Language Specific Sub-network for Multilingual Machine Translationcited by 48
38 more
- 2023Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decodingcited by 42
- 2021Counter-Interference Adapter for Multilingual Machine Translationcited by 39
- 2021Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitutioncited by 31
- 2021Improving Multilingual Translation by Representation and Gradient Regularizationcited by 31
- 2021Language Tags Matter for Zero-Shot Neural Machine Translationcited by 29
- 2022Using natural language prompts for machine translationcited by 27
- 2022Examining Scaling and Transfer of Language Model Architectures for Machine Translationcited by 26
- 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
- 2021Can You Traducir This? Machine Translation for Code-Switched Inputcited by 21
- 2022Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translationcited by 21
- 2022How Robust is Neural Machine Translation to Language Imbalance in Multilingual Tokenizer Training?cited by 20
- 2022Towards the Next 1000 Languages in Multilingual Machine Translation: Exploring the Synergy Between Supervised and Self-Supervised Learningcited by 19
- 2021Distributionally Robust Multilingual Machine Translationcited by 18
- 2021Tricks for Training Sparse Translation Modelscited by 17
- 2021A Survey on Low-Resource Neural Machine Translationcited by 16
- 2021Bandits Don't Follow Rules: Balancing Multi-Facet Machine Translation with Multi-Armed Banditscited by 16
- 2022SMaLL-100: Introducing Shallow Multilingual Machine Translation Model for Low-Resource Languagescited by 16
- 2021Rethinking Zero-shot Neural Machine Translation: From a Perspective of Latent Variablescited by 14
- 2022Language-Family Adapters for Low-Resource Multilingual Neural Machine Translationcited by 14
- 2021Efficient Weight factorization for Multilingual Speech Recognitioncited by 12
- 2021Continual Learning in Multilingual NMT via Language-Specific Embeddingscited by 12
- 2022Universal Conditional Masked Language Pre-training for Neural Machine Translationcited by 12
- 2022Multilingual Neural Machine Translation with Deep Encoder and Multiple Shallow Decoderscited by 12
- 2022MMTAfrica: Multilingual Machine Translation for African Languagescited by 11
- 2023Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weightscited by 11
- 2021Multilingual Translation via Grafting Pre-trained Language Modelscited by 10
- 2023Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularizationcited by 10
- 2023Towards Higher Pareto Frontier in Multilingual Machine Translationcited by 9
- 2021Breaking Down Multilingual Machine Translationcited by 8
- 2023Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adaptercited by 8
- 2024AnyTrans: Translate AnyText in the Image with Large Scale Modelscited by 8
- 2021Low-Resource Neural Machine Translation for Southern African Languagescited by 7
- 2021Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documentscited by 7
- 2022Multilingual Mix: Example Interpolation Improves Multilingual Neural Machine Translationcited by 7
- 2023Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translationcited by 7
- 2023Order Matters in the Presence of Dataset Imbalance for Multilingual Learningcited by 7
50 most cited of 117 All 117 (JSON)
- 2026Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study4 Aug 2026
- 2026The Impact of Vocabulary Overlaps on Knowledge Transfer in Multilingual Machine Translation5 May 2026
- 2025FuxiMT: Sparsifying Large Language Models for Chinese-Centric Multilingual Machine Translation20 May 2025
- 2025Joint Training And Decoding for Multilingual End-to-End Simultaneous Speech Translation14 Mar 2025
- 2025Contextual Cues in Machine Translation: Investigating the Potential of Multi-Source Input Strategies in LLMs and NMT Systems10 Mar 2025
- 2025How Vital is the Jurisprudential Relevance: Law Article Intervened Legal Case Retrieval and Matching25 Feb 2025
- 2025Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation6 Feb 2025
- 2024CULL-MT: Compression Using Language and Layer pruning for Machine Translation10 Nov 2024
- 2024Can the Variation of Model Weights be used as a Criterion for Self-Paced Multilingual NMT?5 Oct 2024
- 2024Parallel Corpus Augmentation using Masked Language Models4 Oct 2024
- 2024Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach14 Aug 2024
- 2024Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features2 Aug 2024
38 more
- 2024AnyTrans: Translate AnyText in the Image with Large Scale Models17 Jun 2024
- 2024Investigating the translation capabilities of Large Language Models trained on parallel data only13 Jun 2024
- 2024LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translation5 Jun 2024
- 2024A Systematic Analysis of Subwords and Cross-Lingual Transfer in Multilingual Translation29 Mar 2024
- 2023Order Matters in the Presence of Dataset Imbalance for Multilingual Learning11 Dec 2023
- 2023Investigating Multi-Pivot Ensembling with Massively Multilingual Machine Translation Models13 Nov 2023
- 2023Is Robustness Transferable across Languages in Multilingual Neural Machine Translation?31 Oct 2023
- 2023How To Build Competitive Multi-gender Speech Translation Models For Controlling Speaker Gender Translation23 Oct 2023
- 2023Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights19 Oct 2023
- 2023Direct Neural Machine Translation with Task-level Mixture of Experts models18 Oct 2023
- 2023Unlikelihood Tuning on Negative Samples Amazingly Improves Zero-Shot Translation28 Sep 2023
- 2023A Benchmark for Learning to Translate a New Language from One Grammar Book28 Sep 2023
- 2023Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding13 Sep 2023
- 2023An Ensemble Approach to Personalized Real Time Predictive Writing for Experts25 Aug 2023
- 2023Unsupervised anomalies detection in IIoT edge devices networks using federated learning23 Aug 2023
- 2023Exploring Linguistic Similarity and Zero-Shot Learning for Multilingual Translation of Dravidian Languages10 Aug 2023
- 2023SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills28 Jun 2023
- 2023Towards Higher Pareto Frontier in Multilingual Machine Translation25 May 2023
- 2023Exploring Representational Disparities Between Multilingual and Bilingual Translation Models23 May 2023
- 2023Communication Efficient Federated Learning for Multilingual Neural Machine Translation with Adapter21 May 2023
- 2023Variable-length Neural Interlingua Representations for Zero-shot Neural Machine Translation17 May 2023
- 2023Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularization12 May 2023
- 2023Train Global, Tailor Local: Minimalist Multilingual Translation into Endangered Languages5 May 2023
- 2023An Empirical Study of Leveraging Knowledge Distillation for Compressing Multilingual Neural Machine Translation Models19 Apr 2023
- 2023Exploiting Multilingualism in Low-resource Neural Machine Translation via Adversarial Learning31 Mar 2023
- 2023Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translation27 Mar 2023
- 2023Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOM3 Mar 2023
- 2023Efficiently Upgrading Multilingual Machine Translation Models to Support More Languages7 Feb 2023
- 2023Multilingual Entity and Relation Extraction from Unified to Language-specific Training11 Jan 2023
- 2022Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation20 Dec 2022
- 2022Causes and Cures for Interference in Multilingual Translation14 Dec 2022
- 2022Life-long Learning for Multilingual Neural Machine Translation with Knowledge Distillation6 Dec 2022
- 2022Learning an Artificial Language for Knowledge-Sharing in Multilingual Translation2 Nov 2022
- 2022Improving Zero-Shot Multilingual Translation with Universal Representations and Cross-Mappings28 Oct 2022
- 2022Robust Domain Adaptation for Pre-trained Multilingual Neural Machine Translation Models26 Oct 2022
- 2022SIT at MixMT 2022: Fluent Translation Built on Giant Pre-trained Models21 Oct 2022
- 2022DIICAN: Dual Time-scale State-Coupled Co-estimation of SOC, SOH and RUL for Lithium-Ion Batteries20 Oct 2022
- 2022Can Domains Be Transferred Across Languages in Multi-Domain Multilingual Neural Machine Translation?20 Oct 2022
50 newest of 117 All 117 (JSON)
- 2021Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languagescited by 133
- 2021Neural Machine Translation for Low-Resource Languages: A Surveycited by 108
- 2022A Few Thousand Translations Go a Long Way! Leveraging Pre-trained Models for African News Translationcited by 97
- 2021Survey of Low-Resource Machine Translationcited by 92
- 2023A Benchmark for Learning to Translate a New Language from One Grammar Bookcited by 74
- 2022Building Machine Translation Systems for the Next Thousand Languagescited by 69
- 2023Investigating the Translation Performance of a Large Multilingual Language Model: the Case of BLOOMcited by 58
- 2021Facebook AI WMT21 News Translation Task Submissioncited by 57
- 2021A Survey on Green Deep Learningcited by 52
- 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
- 2021Learning Language Specific Sub-network for Multilingual Machine Translationcited by 48
- 2023Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decodingcited by 42
12 most cited of 114 All 114 (JSON)
- 2026Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study4 Aug 2026
- 2026The Impact of Vocabulary Overlaps on Knowledge Transfer in Multilingual Machine Translation5 May 2026
- 2025FuxiMT: Sparsifying Large Language Models for Chinese-Centric Multilingual Machine Translation20 May 2025
- 2025Joint Training And Decoding for Multilingual End-to-End Simultaneous Speech Translation14 Mar 2025
- 2025Contextual Cues in Machine Translation: Investigating the Potential of Multi-Source Input Strategies in LLMs and NMT Systems10 Mar 2025
- 2025How Vital is the Jurisprudential Relevance: Law Article Intervened Legal Case Retrieval and Matching25 Feb 2025
- 2025Multilingual Non-Autoregressive Machine Translation without Knowledge Distillation6 Feb 2025
- 2024CULL-MT: Compression Using Language and Layer pruning for Machine Translation10 Nov 2024
- 2024Can the Variation of Model Weights be used as a Criterion for Self-Paced Multilingual NMT?5 Oct 2024
- 2024Parallel Corpus Augmentation using Masked Language Models4 Oct 2024
- 2024Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach14 Aug 2024
- 2024Improving Multilingual Neural Machine Translation by Utilizing Semantic and Linguistic Features2 Aug 2024
12 newest of 114 All 114 (JSON)