# Extremely low-resource machine translation for closely related languages

arXiv: https://arxiv.org/abs/2105.13065 · HTML: https://mlsanity.com/paper/2105.13065/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 27 May 2021.

## Builds on (most cited first, 17 of 17)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation](https://mlsanity.com/paper/2004.11867/) (2020)
- [Universal Dependencies v2: An Evergrowing Multilingual Treebank Collection](https://mlsanity.com/paper/2004.10643/) (2020)
- [Phrase-Based & Neural Unsupervised Machine Translation](https://mlsanity.com/paper/1804.07755/) (2018)
- [Universal Neural Machine Translation for Extremely Low Resource Languages](https://mlsanity.com/paper/1802.05368/) (2018)
- [Unsupervised Statistical Machine Translation](https://mlsanity.com/paper/1809.01272/) (2018)
- [Trivial Transfer Learning for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1809.00357/) (2018)
- [Linguistic Input Features Improve Neural Machine Translation](https://mlsanity.com/paper/1606.02892/) (2016)
- [Sockeye: A Toolkit for Neural Machine Translation](https://mlsanity.com/paper/1712.05690/) (2017)
- [Multi-Domain Neural Machine Translation](https://mlsanity.com/paper/1805.02282/) (2018)
- [Neural Machine Translation into Language Varieties](https://mlsanity.com/paper/1811.01064/) (2018)
- [A Neural Approach to Language Variety Translation](https://mlsanity.com/paper/1807.00651/) (2018)
- [Improving Multilingual Neural Machine Translation For Low-Resource Languages: French,English - Vietnamese](https://mlsanity.com/paper/2012.08743/) (2020)

## Built on by (most cited first, 7 of 7)

- [Disentangling Singlish Discourse Particles with Task-Driven Representation](https://mlsanity.com/paper/2409.20366/) (2024)
- [Data-adaptive Transfer Learning for Translation: A Case Study in Haitian and Jamaican](https://mlsanity.com/paper/2209.06295/) (2022)
- [LLMs for Extremely Low-Resource Finno-Ugric Languages](https://mlsanity.com/paper/2410.18902/) (2024)
- [CycleDistill: Bootstrapping Machine Translation using LLMs with Cyclical Distillation](https://mlsanity.com/paper/2506.19952/) (2025)
- [Contrastive Token Learning with Similarity Decay for Repetition Suppression in Machine Translation](https://mlsanity.com/paper/2409.19877/) (2024)
- [Limited-Resource Adapters Are Regularizers, Not Linguists](https://mlsanity.com/paper/2505.24525/) (2025)
- [Cross-Lingual Transfer for Machine Translation in Turkic Languages](https://mlsanity.com/paper/2607.29355/) (2026)

## 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.