AI engineering glossary · NLP embeddings
What is contextual embedding?
Contextual embedding (also called Contextualised word embedding): A word vector computed from the whole sentence, so the same word gets different vectors in different contexts. Deep sequence models produce them and they capture word senses far better than static vectors.
Contextual embedding: an example
"bat" gets one vector in "he swung the bat" and a clearly different one in "the bat flew out".
Related terms
More NLP embeddings terms
- Continuous bag of words
- Coreference resolution
- Corpus
- Cross-encoder
- Cross-lingual transfer
- Dependency parsing
- Distributional hypothesis
- Document-term matrix
Where you learn it
Contextual 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.