1. 程式人生 > >[深度學習]從Attention到Transformer到BERT

[深度學習]從Attention到Transformer到BERT

Jay Alammar用直觀直白的方式解釋了Attention,Transformer和BERT。並輔以很多生動的圖例。

Attention

Visualizing A Neural Machine Translation Model (Mechanics of Seq2seq Models With Attention)

Transformer

The Illustrated Transformer

BERT

The Illustrated BERT, ELMo, and co. (How NLP Cracked Transfer Learning)

其他資料

NLP's ImageNet moment has arrived