@article{lowrankfactorizationforcompactmultihead, title = {Low Rank Factorization for Compact Multi-Head Self-Attention}, author = {Sneha Mehta and Huzefa Rangwala and Naren Ramakrishnan}, year = {2019}, eprint = {1912.00835}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/1912.00835v2}, }