@article{attentivestudentmeetsmultitaskteacher, title = {MKD: a Multi-Task Knowledge Distillation Approach for Pretrained Language Models}, author = {Linqing Liu and Huan Wang and Jimmy Lin and Richard Socher and Caiming Xiong}, year = {2019}, eprint = {1911.03588}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1911.03588v2}, }