@article{debertav3improvingdebertausingelectra, title = {DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing}, author = {Pengcheng He and Jianfeng Gao and Weizhu Chen}, year = {2021}, eprint = {2111.09543}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2111.09543v4}, }