mlsanityData to 7 Oct 2026

Extremely low-resource machine translation for closely related languages

arXiv 2105.13065 ↗First posted 27 May 2021cs.CLcited by 7

Not on the map. Why?

Abstract (arXiv)

An effective method to improve extremely low-resource neural machine translation is multilingual training, which can be improved by leveraging monolingual data to create synthetic bilingual corpora using the back-translation method. This work focuses on closely related languages from the Uralic language family: from Estonian and Finnish geographical regions. We find that multilingual learning and synthetic corpora increase the translation quality in every language pair for which we have data. We show that transfer learning and fine-tuning are very effective for doing low-resource machine translation and achieve the best results. We collected new parallel data for V~oro, North and South Saami and present first results of neural machine translation for these languages.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 17 of its 33 references that are in the map. First posted on arXiv 27 May 2021.

Builds on

17 of 33 references.

References · 17

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  3. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  4. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  5. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
  6. 2020Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translationcited by 277
  7. 2020Universal Dependencies v2: An Evergrowing Multilingual Treebank Collectioncited by 269
  8. 2018Phrase-Based & Neural Unsupervised Machine Translationcited by 138
  9. 2018Universal Neural Machine Translation for Extremely Low Resource Languagescited by 66
  10. 2018Unsupervised Statistical Machine Translationcited by 51
  11. 2018Trivial Transfer Learning for Low-Resource Neural Machine Translationcited by 47
  12. 2016Linguistic Input Features Improve Neural Machine Translationcited by 38
5 more
  1. 2017Sockeye: A Toolkit for Neural Machine Translationcited by 15
  2. 2018Multi-Domain Neural Machine Translationcited by 11
  3. 2018Neural Machine Translation into Language Varietiescited by 9
  4. 2018A Neural Approach to Language Variety Translationcited by 6
  5. 2020Improving Multilingual Neural Machine Translation For Low-Resource Languages: French,English - Vietnamesecited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 3; 2025: 2; 2026: 1.

7 papers.

  1. 2024Disentangling Singlish Discourse Particles with Task-Driven Representationcited by 5
  2. 2022Data-adaptive Transfer Learning for Translation: A Case Study in Haitian and Jamaicancited by 3
  3. 2024LLMs for Extremely Low-Resource Finno-Ugric Languagescited by 3
  4. 2024Contrastive Token Learning with Similarity Decay for Repetition Suppression in Machine Translationcited by 1
  5. 2025CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillationcited by 1
  6. 2025Limited-Resource Adapters Are Regularizers, Not Linguistscited by 0
  7. 2026Cross-Lingual Transfer for Machine Translation in Turkic Languagescited by 0