Language Understanding with BERT

The most useful deep learning model

A schematic depiction of the BERT model and its training process (from [1])

What is BERT?

Bidirectional Encoder Representations from Transformers (BERT) [1] is a popular deep learning model that is used for numerous different language understanding tasks. BERT shares the same architecture as a transformer encoder, and is extensively pre-trained on raw, unlabeled textual data using a…