@inproceedings{onlayernormalizationinthetransformer1, title = {On Layer Normalization in the Transformer Architecture}, author = {Ruibin Xiong and Yunchang Yang and Di He and Kai Zheng and Shuxin Zheng and Chen Xing and Huishuai Zhang and Yanyan Lan and Li-Wei Wang and Tie-Yan Liu}, year = {2020}, booktitle = {ICML 2020 1}, eprint = {2002.04745}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2002.04745v2}, }