AI engineering glossary · NLP embeddings
What is skip-gram?
Skip-gram (also called Skip-gram model): A Word2Vec architecture that takes one centre word and learns to predict the words around it within a window. It works well for rare words and small corpora, and its learned input weights become the word vectors.
Skip-gram: an example
For "we drink hot chai" with centre word "hot", the model tries to predict "drink" and "chai".
Related terms
More NLP embeddings terms
- Slot filling
- Smoothing
- spaCy
- Special tokens
- Spelling correction
- Static embedding
- Subword regularisation
- Subword tokenisation
Where you learn it
Skip-gram is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.