@article{fastertransformerdecodingngrammasked, title = {Faster Transformer Decoding: N-gram Masked Self-Attention}, author = {Ciprian Chelba and Mia Chen and Ankur Bapna and Noam Shazeer}, year = {2020}, eprint = {2001.04589}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2001.04589v2}, }