Look Backward and Forward: Self-Knowledge Distillation with Bidirectional Decoder for Neural Machine Translation

Neural Machine Translation(NMT) models are usually trained via unidirectional decoder which corresponds to optimizing one-step-ahead prediction. However, this kind of unidirectional decoding framework may incline to focus on local structure rather than global coherence. To alleviate this problem, we propose a novel method, Self-Knowledge Distillation with Bidirectional Decoder for Neural Machine Translation(SBD-NMT). We deploy a backward decoder which can act as an effective regularization method to the forward decoder. By leveraging the backward decoder's information about the longer-term future, distilling knowledge learned in the backward decoder can encourage auto-regressive NMT models to plan ahead. Experiments show that our method is significantly better than the strong Transformer baselines on multiple machine translation data sets. Our codes will be released on github soon.