Yanjun Miao

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

2022 · arXiv (Cornell University)

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 …