@article{multilayersoftmaxingduringtrainingneural, title = {Multi-Layer Softmaxing during Training Neural Machine Translation for Flexible Decoding with Fewer Layers}, author = {Raj Dabre and Atsushi Fujita}, year = {2019}, eprint = {1908.10118}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1908.10118v2}, }