AI engineering glossary · NLP embeddings
What is word analogy?
Word analogy (also called Analogy task): A test of embeddings that checks whether vector arithmetic reflects relationships, such as king - man + woman landing near queen. It is a popular, though imperfect, way to show that embeddings capture regularities.
Word analogy: an example
In some embeddings, vec(Paris) - vec(France) + vec(India) is closest to vec(Delhi).
Related terms
More NLP embeddings terms
- Word embedding
- Word sense disambiguation
- Word tokenisation
- Word2Vec
- WordPiece
- Zipf's law
- Agglutinative language
- Backoff
Where you learn it
Word analogy is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.