AI engineering glossary · NLP embeddings
What is WSD (word sense disambiguation)?
Word sense disambiguation (also called WSD): Choosing the correct meaning of a word that has several senses, using its surrounding context. Static embeddings blend all senses of a word into one vector, so context-aware methods are usually needed to tell the senses apart.
Word sense disambiguation: an example
In "He deposited cash at the bank", "bank" means a financial institution, not a river edge.
Related terms
More NLP embeddings terms
- Word tokenisation
- Word2Vec
- WordPiece
- Zipf's law
- Agglutinative language
- Backoff
- Bi-encoder
- Bidirectional LSTM-CRF
Where you learn it
Word sense disambiguation is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.