Back to Reading Room

LA BIBLIOTHÈQUE · READING NOTE

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Devlin et al.

To Read · 想看

AINLPPapers

BERT, Pretraining, Masked Language Modeling, Transformer

通过双向 Transformer Encoder 和 Masked Language Modeling 进行预训练,再针对下游任务微调,使 Pretrain-Finetune 成为 NLP 主流范式。