Glossary Entry

Embedding

A dense numeric representation that places similar items close together in vector space.

Representation NLP

Also called: vector embedding, embedding vector

Seed source: Google ML Glossary

Embeddings turn text, images, users, products, or other entities into arrays of numbers that models can compare efficiently. Similar items usually end up near each other, which is why embeddings are useful for search, recommendation, ranking, and clustering.

In many blog examples, embeddings are the bridge between messy human language and a system that can perform fast similarity lookup.