@article{acceleratingtransformerdecodingviaa, title = {Accelerating Transformer Decoding via a Hybrid of Self-attention and Recurrent Neural Network}, author = {Chengyi Wang and Shuangzhi Wu and Shujie Liu}, year = {2019}, eprint = {1909.02279}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1909.02279v1}, }