AI engineering glossary · NLP embeddings
What is mean pooling?
Mean pooling (also called Average pooling of tokens): Producing one vector for a text by averaging the vectors of all its tokens, usually ignoring padding positions. It is a simple, common way to turn token-level outputs into a sentence embedding.
Mean pooling: an example
Averaging three token vectors [1, 2], [3, 4], [5, 6] gives [3, 4].
Related terms
More NLP embeddings terms
- Morphology
- Multilingual embedding
- N-gram
- N-gram language model
- Named entity
- Named entity recognition
- Natural language processing
- Natural language understanding
Where you learn it
Mean pooling is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.