AI engineering glossary · NLP embeddings
What is gazetteer?
Gazetteer: A list of known names, such as cities, companies or drug names, used to help find entities in text. Matching against it gives useful features to entity recognisers but cannot alone handle new or ambiguous names.
Gazetteer: an example
A gazetteer of 700 Indian district names helps flag "Nashik" as a location.
Related terms
More NLP embeddings terms
- GloVe
- Hard negative mining
- Hidden Markov model
- Hierarchical softmax
- In-batch negatives
- InfoNCE loss
- Intent classification
- Inverse document frequency
Where you learn it
Gazetteer is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.