AI engineering glossary · NLP embeddings
What is SBERT (Sentence-BERT)?
Sentence-BERT (also called SBERT): An approach that fine-tunes a BERT-style model in a twin (siamese) setup so that pooled outputs of two sentences can be compared directly with cosine similarity. It makes semantic search over thousands of sentences fast, since each sentence is encoded only once.
Sentence-BERT: an example
Encoding 100,000 FAQ answers once with SBERT lets a query be matched by one encoding and quick vector comparisons.
Related terms
More NLP embeddings terms
Where you learn it
Sentence-BERT is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.