What is Named Entity Recognition (NER)?
Named Entity Recognition (NER) — An NLP technique that identifies and classifies key entities in text into predefined categories.
NER automatically identifies and classifies named entities in text — people, organizations, locations, dates, monetary values, and more. It powers data extraction from documents, contract analysis, and structured information retrieval from unstructured text.
Frequently Asked Questions
What entities can NER detect?
Standard categories include person names, organizations, locations, dates, monetary values, and percentages. Custom NER models can be trained to detect domain-specific entities like drug names or product codes.
How accurate is NER?
State-of-the-art models achieve 90-95% F1 scores on standard entity types. LLMs can perform NER zero-shot with comparable accuracy, eliminating the need for custom training in many cases.
What is the difference between NER and text classification?
Text classification assigns labels to entire documents. NER identifies and labels specific spans of text within a document. They solve different problems and are often used together.