AI engineering glossary · NLP embeddings
What is sentence embedding?
Sentence embedding (also called Text embedding, Sentence vector): A single dense vector that represents the meaning of a whole sentence or short passage, so texts with similar meaning have nearby vectors. It powers semantic search, clustering, duplicate detection and retrieval systems.
Sentence embedding: an example
"How do I reset my UPI PIN?" and "Forgot my UPI PIN, what now?" get vectors with cosine similarity around 0.9.
Related terms
More NLP embeddings terms
- Sentence segmentation
- Sentence-BERT
- SentencePiece
- Sentiment analysis
- Sequence labelling
- Siamese network
- Skip-gram
- Slot filling
Where you learn it
Sentence embedding is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.