Bi-Directional Neural Machine Translation with Synthetic Parallel Data
This addresses translation quality issues in low-resource and cross-domain scenarios, offering a cost-effective solution, though it is incremental as it builds on existing back-translation and multilingual approaches.
The paper tackles the problem of low-resource and out-of-domain Neural Machine Translation by proposing a technique that combines back-translation and multilingual NMT, resulting in improved performance and reduced costs compared to standard methods.
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.