# Neural machine translation for low-resource languages

arXiv: https://arxiv.org/abs/1708.05729 · HTML: https://mlsanity.com/paper/1708.05729/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Aug 2017.

## Built on by (most cited first, 8 of 8)

- [Neural Machine Translation for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2106.15115/) (2021)
- [Family of Origin and Family of Choice: Massively Parallel Lexiconized Iterative Pretraining for Severely Low Resource Machine Translation](https://mlsanity.com/paper/2104.05848/) (2021)
- [Artificial intelligence contribution to translation industry: looking back and forward](https://mlsanity.com/paper/2411.19855/) (2024)
- [Dict-NMT: Bilingual Dictionary based NMT for Extremely Low Resource Languages](https://mlsanity.com/paper/2206.04439/) (2022)
- [Composing RNNs and FSTs for Small Data: Recovering Missing Characters in Old Hawaiian Text](https://mlsanity.com/paper/2208.10248/) (2022)
- [NusaMT-7B: Machine Translation for Low-Resource Indonesian Languages with Large Language Models](https://mlsanity.com/paper/2410.07830/) (2024)
- [Understanding and Enhancing the Use of Context for Machine Translation](https://mlsanity.com/paper/2102.10437/) (2021)
- [Massively Multilingual Text Translation For Low-Resource Languages](https://mlsanity.com/paper/2401.16582/) (2024)

## Abstract (arXiv)

Neural machine translation (NMT) approaches have improved the state of the art in many machine translation settings over the last couple of years, but they require large amounts of training data to produce sensible output. We demonstrate that NMT can be used for low-resource languages as well, by introducing more local dependencies and using word alignments to learn sentence reordering during translation. In addition to our novel model, we also present an empirical evaluation of low-resource phrase-based statistical machine translation (SMT) and NMT to investigate the lower limits of the respective technologies. We find that while SMT remains the best option for low-resource settings, our method can produce acceptable translations with only 70000 tokens of training data, a level where the baseline NMT system fails completely.