BERT
Links
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (24/05/2019)
How to Fine Tune Bert for Sequence Classification?
https://www.kaggle.com/discussions/questions-and-answers/86510
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (SBERT): modello successivo a BERT con migliori risultati sui benchmark di Semantic Textual Similarity (STS)
https://discuss.huggingface.co/t/significance-of-the-cls-token/3180