What is BERT?

NLP

BERT — Bidirectional Encoder Representations from Transformers. A pre-trained language model by Google that understands context from both directions. Used for classification, NER, and embeddings.

FAQ

What is BERT?

A bidirectional transformer model by Google, pre-trained on masked language modeling. Excellent for understanding text (classification, search, NER).

BERT vs GPT?

BERT is bidirectional (understands context from both sides) — good for understanding. GPT is autoregressive (left-to-right) — good for generation.

Related Terms

Learn BERT in depth

Free hands-on course with code examples and Google Colab notebooks.

Start Course →