@inproceedings{extremelylowbittransformerquantization, title = {Extremely Low Bit Transformer Quantization for On-Device Neural Machine Translation}, author = {Insoo Chung and Byeongwook Kim and Yoonjung Choi and Se Jung Kwon and Yongkweon Jeon and Baeseong Park and Sangha Kim and Dongsoo Lee}, year = {2020}, booktitle = {Findings of the Association for Computational Linguistics 2020}, eprint = {2009.07453}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2009.07453v2}, }