# Bi-Directional Neural Machine Translation with Synthetic Parallel Data

arXiv: https://arxiv.org/abs/1805.11213 · HTML: https://mlsanity.com/paper/1805.11213/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2018.

## Built on by (most cited first, 11 of 11)

- [A Survey on Low-Resource Neural Machine Translation](https://mlsanity.com/paper/2107.04239/) (2021)
- [Cross-language Sentence Selection via Data Augmentation and Rationale Training](https://mlsanity.com/paper/2106.02293/) (2021)
- [Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languages](https://mlsanity.com/paper/2107.08772/) (2021)
- [Segmenting Subtitles for Correcting ASR Segmentation Errors](https://mlsanity.com/paper/2104.07868/) (2021)
- [HintedBT: Augmenting Back-Translation with Quality and Transliteration Hints](https://mlsanity.com/paper/2109.04443/) (2021)
- [Bi-Mix: Bidirectional Mixing for Domain Adaptive Nighttime Semantic Segmentation](https://mlsanity.com/paper/2111.10339/) (2021)
- [Multilingual Bidirectional Unsupervised Translation Through Multilingual Finetuning and Back-Translation](https://mlsanity.com/paper/2209.02821/) (2022)
- [Extending Multilingual Machine Translation through Imitation Learning](https://mlsanity.com/paper/2311.08538/) (2023)
- [The Impact of Syntactic and Semantic Proximity on Machine Translation with Back-Translation](https://mlsanity.com/paper/2403.18031/) (2024)
- [Mitigating Semantic Leakage in Cross-lingual Embeddings via Orthogonality Constraint](https://mlsanity.com/paper/2409.15664/) (2024)
- [Back-Translation Still Matters: Leveraging Monolingual Data for Low-Resource Machine Translation with LLMs](https://mlsanity.com/paper/2610.18818/) (2026)

## Abstract (arXiv)

Despite impressive progress in high-resource settings, Neural Machine Translation (NMT) still struggles in low-resource and out-of-domain scenarios, often failing to match the quality of phrase-based translation. We propose a novel technique that combines back-translation and multilingual NMT to improve performance in these difficult cases. Our technique trains a single model for both directions of a language pair, allowing us to back-translate source or target monolingual data without requiring an auxiliary model. We then continue training on the augmented parallel data, enabling a cycle of improvement for a single model that can incorporate any source, target, or parallel data to improve both translation directions. As a byproduct, these models can reduce training and deployment costs significantly compared to uni-directional models. Extensive experiments show that our technique outperforms standard back-translation in low-resource scenarios, improves quality on cross-domain tasks, and effectively reduces costs across the board.