AI engineering glossary · NLP embeddings
What is semantic similarity?
Semantic similarity (also called Semantic relatedness): How close two pieces of text are in meaning, regardless of the exact words used. In practice it is estimated by comparing the embedding vectors of the two texts, often with cosine similarity, and it is the basis of semantic search and duplicate detection.
Semantic similarity: an example
"cheap flights to Goa" and "low-cost air tickets to Goa" have high semantic similarity though they share few words.
Related terms
More NLP embeddings terms
- Semantic textual similarity
- Sentence embedding
- Sentence segmentation
- Sentence-BERT
- SentencePiece
- Sentiment analysis
- Sequence labelling
- Siamese network
Where you learn it
Semantic similarity is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.