This chapter takes a deep dive into the BERT algorithm for sentence embedding along with various training strategies, including MLM and NSP. We will also see an implementation of a text classification system using BERT.
How Does BERT Work?
BERT makes use of a transformer to learn contextual relations between words in a text. A transformer has two mechanisms—an encoder and a decoder—but BERT only requires the encoder mechanism. BERT uses a bidirectional approach and reads the text input sequentially, ...
