@inproceedings{optimizingdeepertransformersonsmall, title = {Optimizing Deeper Transformers on Small Datasets}, author = {Peng Xu and Dhruv Kumar and Wei Yang and Wenjie Zi and Keyi Tang and Chenyang Huang and Jackie Chi Kit Cheung and Simon J. D. Prince and Yanshuai Cao}, year = {2020}, booktitle = {ACL 2021 5}, eprint = {2012.15355}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2012.15355v4}, }