Generalizing Back-Translation in Neural Machine Translation
This work addresses fundamental issues in back-translation for NMT, offering incremental improvements for translation systems.
The authors reformulated back-translation in neural machine translation to clarify its mathematical assumptions and proposed fixes for sampling-based approaches, achieving improvements on the WMT 2018 German-English task.
Back-translation - data augmentation by translating target monolingual data - is a crucial component in modern neural machine translation (NMT). In this work, we reformulate back-translation in the scope of cross-entropy optimization of an NMT model, clarifying its underlying mathematical assumptions and approximations beyond its heuristic usage. Our formulation covers broader synthetic data generation schemes, including sampling from a target-to-source NMT model. With this formulation, we point out fundamental problems of the sampling-based approaches and propose to remedy them by (i) disabling label smoothing for the target-to-source model and (ii) sampling from a restricted search space. Our statements are investigated on the WMT 2018 German - English news translation task.