# Sub-Word Alignment Is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation

arXiv: https://arxiv.org/abs/2205.04067 · HTML: https://mlsanity.com/paper/2205.04067/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 35 references that are in the map.
- First posted on arXiv 9 May 2022.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [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)
- [Word Translation Without Parallel Data](https://mlsanity.com/paper/1710.04087/) (2017)
- [Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation](https://mlsanity.com/paper/1611.04558/) (2016)
- [Six Challenges for Neural Machine Translation](https://mlsanity.com/paper/1706.03872/) (2017)
- [Unsupervised Machine Translation Using Monolingual Corpora Only](https://mlsanity.com/paper/1711.00043/) (2017)
- [Transfer Learning for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1604.02201/) (2016)
- [Unsupervised Neural Machine Translation](https://mlsanity.com/paper/1710.11041/) (2017)
- [Choosing Transfer Languages for Cross-Lingual Learning](https://mlsanity.com/paper/1905.12688/) (2019)
- [Phrase-Based & Neural Unsupervised Machine Translation](https://mlsanity.com/paper/1804.07755/) (2018)
- [Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism](https://mlsanity.com/paper/1601.01073/) (2016)
- [Meta-Learning for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1808.08437/) (2018)
- [Universal Neural Machine Translation for Extremely Low Resource Languages](https://mlsanity.com/paper/1802.05368/) (2018)
- [On the Limitations of Unsupervised Bilingual Dictionary Induction](https://mlsanity.com/paper/1805.03620/) (2018)
- [Transfer Learning across Low-Resource, Related Languages for Neural Machine Translation](https://mlsanity.com/paper/1708.09803/) (2017)
- [Fully Character-Level Neural Machine Translation without Explicit Segmentation](https://mlsanity.com/paper/1610.03017/) (2016)
- [Trivial Transfer Learning for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/1809.00357/) (2018)
- [Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabularies](https://mlsanity.com/paper/1905.05475/) (2019)
- [Neural Machine Translation with Pivot Languages](https://mlsanity.com/paper/1611.04928/) (2016)
- [Towards cross-lingual distributed representations without parallel text trained with adversarial autoencoders](https://mlsanity.com/paper/1608.02996/) (2016)
- [A Universal Parent Model for Low-Resource Neural Machine Translation Transfer](https://mlsanity.com/paper/1909.06516/) (2019)
- [Improving Unsupervised Word-by-Word Translation with Language Model and Denoising Autoencoder](https://mlsanity.com/paper/1901.01590/) (2019)

## Built on by (most cited first, 3 of 3)

- [The first neural machine translation system for the Erzya language](https://mlsanity.com/paper/2209.09368/) (2022)
- [ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation](https://mlsanity.com/paper/2212.04262/) (2022)
- [The first open machine translation system for the Chechen language](https://mlsanity.com/paper/2507.12672/) (2025)

## Abstract (arXiv)

We leverage embedding duplication between aligned sub-words to extend the Parent-Child transfer learning method, so as to improve low-resource machine translation. We conduct experiments on benchmark datasets of My-En, Id-En and Tr-En translation scenarios. The test results show that our method produces substantial improvements, achieving the BLEU scores of 22.5, 28.0 and 18.1 respectively. In addition, the method is computationally efficient which reduces the consumption of training time by 63.8%, reaching the duration of 1.6 hours when training on a Tesla 16GB P100 GPU. All the models and source codes in the experiments will be made publicly available to support reproducible research.