0PricingLogin
NLP Academy · Lesson

Embedding Sentences With BERT

Extract contextual vectors in code.

From Words to Sentences

BERT gives every token its own vector. But often you want one vector for the whole sentence, not each word.

The CLS Token

BERT adds a special token named CLS at the very front of each input. Its output is often used as a sentence summary.

All lessons in this course

  1. Why Context Changes Word Meaning
  2. Masked Language Modeling
  3. Embedding Sentences With BERT
  4. Picking the Right Pre-trained Model
← Back to NLP Academy