SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization

SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization Haoming Jiang author Pengcheng He author Weizhu Chen author Xiaodong Liu author Jianfeng Gao author Tuo Zhao author 2020-07 text Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics Dan Jurafsky editor Joyce Chai editor Natalie Schluter editor Joel Tetreault editor Association for Computational Linguistics Online conference publication jiang-etal-2020-smart 10.18653/v1/2020.acl-main.197 https://aclanthology.org/2020.acl-main.197/ 2020-07 2177 2190