@article{compressinglargescaletransformerbased, title = {Compressing Large-Scale Transformer-Based Models: A Case Study on BERT}, author = {Prakhar Ganesh and Yao Chen and Xin Lou and Mohammad Ali Khan and Yin Yang and Hassan Sajjad and Preslav Nakov and Deming Chen and Marianne Winslett}, year = {2020}, eprint = {2002.11985}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2002.11985v2}, }