Improving Bert Fine-Tuning via Stabilizing Cross-Layer Mutual Information.
Jicun Li, Xingjian Li, Tianyang Wang, Shi Wang, Yanan Cao, Cheng-Zhong Xu, Dejing Dou
Browse the full ICASSP paper archive.
Jicun Li, Xingjian Li, Tianyang Wang, Shi Wang, Yanan Cao, Cheng-Zhong Xu, Dejing Dou
Browse the full ICASSP paper archive.