AI engineering glossary · NLP embeddings
What is static embedding?
Static embedding (also called Static word embedding): A word embedding that gives each word exactly one vector regardless of the sentence it appears in. It is cheap and easy to use, but cannot separate different senses of a word.
Static embedding: an example
"bank" has the same vector in "river bank" and "bank loan" under Word2Vec or GloVe.
Related terms
More NLP embeddings terms
- Subword regularisation
- Subword tokenisation
- Term frequency
- Text classification
- Text embedding model
- Text normalisation
- TF-IDF
- Token
Where you learn it
Static 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.