@article{edgebertoptimizingonchipinferencefor, title = {EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference}, author = {Thierry Tambe and Coleman Hooper and Lillian Pentecost and Tianyu Jia and En-Yu Yang and Marco Donato and Victor Sanh and Paul N. Whatmough and Alexander M. Rush and David Brooks and Gu-Yeon Wei}, year = {2020}, eprint = {2011.14203}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2011.14203v5}, }