mlsanityData to 7 Oct 2026

Universal Neural Machine Translation for Extremely Low Resource Languages

arXiv 1802.05368 ↗First posted 15 Feb 2018cs.CLcited by 66

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a new universal machine translation approach focusing on languages with a limited amount of parallel data. Our proposed approach utilizes a transfer-learning approach to share lexical and sentence level representations across multiple source languages into one target language. The lexical part is shared through a Universal Lexical Representation to support multilingual word-level sharing. The sentence-level sharing is represented by a model of experts from all source languages that share the source encoders with all other languages. This enables the low-resource language to utilize the lexical and sentence representations of the higher resource languages. Our approach is able to achieve 23 BLEU on Romanian-English WMT2016 using a tiny parallel corpus of 6k sentences, compared to the 18 BLEU of strong baseline system which uses multilingual training and back-translation. Furthermore, we show that the proposed approach can achieve almost 20 BLEU on the same dataset through fine-tuning a pre-trained multi-lingual system in a zero-shot setting.

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 14; 2023: 5; 2024: 11; 2025: 5; 2026: 6.

66 papers.

Sort:

By area:

  1. 2021Neural Machine Translation for Low-Resource Languages: A Surveycited by 108
  2. 2021Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inferencecited by 96
  3. 2021Towards Fair Federated Learning with Zero-Shot Data Augmentationcited by 64
  4. 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
  5. 2021Counter-Interference Adapter for Multilingual Machine Translationcited by 39
  6. 2021Towards Continual Learning for Multilingual Machine Translation via Vocabulary Substitutioncited by 31
  7. 2021Continual Mixed-Language Pre-Training for Extremely Low-Resource Neural Machine Translationcited by 29
  8. 2021Language Tags Matter for Zero-Shot Neural Machine Translationcited by 29
  9. 2021Importance-based Neuron Allocation for Multilingual Neural Machine Translationcited by 23
  10. 2022Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translationcited by 21
  11. 2021Think about it! Improving defeasible reasoning by first modeling the question scenariocited by 20
  12. 2024ProxyLM: Predicting Language Model Performance on Multilingual Tasks via Proxy Modelscited by 20
38 more
  1. 2021Text is Text, No Matter What: Unifying Text Recognition using Knowledge Distillationcited by 17
  2. 2021A Survey on Low-Resource Neural Machine Translationcited by 16
  3. 2021Endangered Languages are not Low-Resourced!cited by 14
  4. 2024Optimizing Language Augmentation for Multilingual Large Language Models: A Case Study on Koreancited by 14
  5. 2023How Vocabulary Sharing Facilitates Multilingualism in LLaMA?cited by 12
  6. 2024Small Languages, Big Models: A Study of Continual Training on Languages of Norwaycited by 12
  7. 2023Improving Zero-shot Multilingual Neural Machine Translation by Leveraging Cross-lingual Consistency Regularizationcited by 10
  8. 2021Breaking Down Multilingual Machine Translationcited by 8
  9. 2025Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translationcited by 8
  10. 2021Low-Resource Neural Machine Translation for Southern African Languagescited by 7
  11. 2021Extremely low-resource machine translation for closely related languagescited by 7
  12. 2023Syntax and Domain Aware Model for Unsupervised Program Translationcited by 7
  13. 2021Crowdsourced Phrase-Based Tokenization for Low-Resourced Neural Machine Translation: The Case of Fon Languagecited by 6
  14. 2021When Word Embeddings Become Endangeredcited by 6
  15. 2022CAMERO: Consistency Regularized Ensemble of Perturbed Language Models with Weight Sharingcited by 6
  16. 2021Pay Better Attention to Attention: Head Selection in Multilingual and Multi-Domain Sequence Modelingcited by 5
  17. 2022Life-long Learning for Multilingual Neural Machine Translation with Knowledge Distillationcited by 5
  18. 2024m3P: Towards Multimodal Multilingual Translation with Multimodal Promptcited by 5
  19. 2021Token-wise Curriculum Learning for Neural Machine Translationcited by 4
  20. 2021Family of Origin and Family of Choice: Massively Parallel Lexiconized Iterative Pretraining for Severely Low Resource Machine Translationcited by 4
  21. 2021AUGVIC: Exploiting BiText Vicinity for Low-Resource NMTcited by 4
  22. 2022Enriching Biomedical Knowledge for Low-resource Language Through Large-Scale Translationcited by 4
  23. 2022MTet: Multi-domain Translation for English and Vietnamesecited by 4
  24. 2022Improving Zero-Shot Multilingual Translation with Universal Representations and Cross-Mappingscited by 4
  25. 2022ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translationcited by 4
  26. 2022Manifestations of Xenophobia in AI Systemscited by 4
  27. 2024Introducing Syllable Tokenization for Low-resource Languages: A Case Study with Swahilicited by 4
  28. 2022Sub-Word Alignment Is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translationcited by 3
  29. 2021Revisiting Language Encoding in Learning Multilingual Representationscited by 2
  30. 2021Bilingual Dictionary-based Language Model Pretraining for Neural Machine Translationcited by 2
  31. 2022Cross-lingual Word Embeddings in Hyperbolic Spacecited by 2
  32. 2023Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrixcited by 2
  33. 2024Could We Have Had Better Multilingual LLMs If English Was Not the Central Language?cited by 2
  34. 2024Learning-From-Mistakes Prompting for Indigenous Language Translationcited by 2
  35. 2025Compensating for Data with Reasoning: Low-Resource Machine Translation with LLMscited by 2
  36. 2022Informative Language Representation Learning for Massively Multilingual Neural Machine Translationcited by 1
  37. 2022MALM: Mixing Augmented Language Modeling for Zero-Shot Machine Translationcited by 1
  38. 2022Robust Unsupervised Cross-Lingual Word Embedding using Domain Flow Interpolationcited by 1

50 most cited of 66 All 66 (JSON)