# Zero-Shot Dual Machine Translation

arXiv: https://arxiv.org/abs/1805.10338 · HTML: https://mlsanity.com/paper/1805.10338/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2018.

## Built on by (most cited first, 6 of 6)

- [Neural Machine Translation for Low-Resource Languages: A Survey](https://mlsanity.com/paper/2106.15115/) (2021)
- [Using natural language prompts for machine translation](https://mlsanity.com/paper/2202.11822/) (2022)
- [Modeling Dual Read/Write Paths for Simultaneous Machine Translation](https://mlsanity.com/paper/2203.09163/) (2022)
- [Improving Zero-shot Neural Machine Translation on Language-specific Encoders-Decoders](https://mlsanity.com/paper/2102.06578/) (2021)
- [Self-Learning for Zero Shot Neural Machine Translation](https://mlsanity.com/paper/2103.05951/) (2021)
- [Exploring Linguistic Similarity and Zero-Shot Learning for Multilingual Translation of Dravidian Languages](https://mlsanity.com/paper/2308.05574/) (2023)

## Abstract (arXiv)

Neural Machine Translation (NMT) systems rely on large amounts of parallel data. This is a major challenge for low-resource languages. Building on recent work on unsupervised and semi-supervised methods, we present an approach that combines zero-shot and dual learning. The latter relies on reinforcement learning, to exploit the duality of the machine translation task, and requires only monolingual data for the target language pair. Experiments show that a zero-shot dual system, trained on English-French and English-Spanish, outperforms by large margins a standard NMT system in zero-shot translation performance on Spanish-French (both directions). The zero-shot dual method approaches the performance, within 2.2 BLEU points, of a comparable supervised setting. Our method can obtain improvements also on the setting where a small amount of parallel data for the zero-shot language pair is available. Adding Russian, to extend our experiments to jointly modeling 6 zero-shot translation directions, all directions improve between 4 and 15 BLEU points, again, reaching performance near that of the supervised setting.