@article{smartbirdlearnablesparseattentionfor, title = {Smart Bird: Learnable Sparse Attention for Efficient and Effective Transformer}, author = {Chuhan Wu and Fangzhao Wu and Tao Qi and Binxing Jiao and Daxin Jiang and Yongfeng Huang and Xing Xie}, year = {2021}, eprint = {2108.09193}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2108.09193v3}, }