Improving BERT Fine-Tuning via Self-Ensemble and Self-Distillation.

Yige Xu Xipeng Qiu Ligao Zhou Xuanjing Huang

Published in: CoRR (2020)

Keyphrases

fine tuning
viable alternative
fine tune
fine tuned
neural network
ensemble learning
training data
genetic algorithm
computer vision
bayesian networks
training set
evolutionary algorithm
random forests
regression problems
classifier ensemble
ensemble pruning