Link to the slides: **https://t.ly/8u6B**

More reading:

Transformer: Attention Is All You Need

The annotated attention

Illustrated Transformer: http://jalammar.github.io/illustrated-transformer/

BERT’s tokenizer: WordPiece Explore BERT Embeddings with colab: https://colab.research.google.com/drive/1yFphU6PW9Uo6lmDly_ud9a6c4RCYlwdX?usp=sharing