Beta. Content is under active construction and has not been peer-reviewed. Report errors on GitHub.Disclaimer

BERT and the Pretrain-Finetune Paradigm

3 questionsDifficulty 2-4View topic
Foundation
0 / 3
2 foundation1 intermediateAdapts to your performance
1 / 3
foundation (2/10)conceptual
The pretrain-then-finetune paradigm popularized by BERT (2018) has become standard for NLP. What is the key advantage over training from scratch on each task?