Named Entity Recognition (NER)
An NLP task that identifies and classifies named entities in text into predefined categories like person names, organizations, locations, dates, and monetary values.
How It Works
NER models tag each token in a sentence with an entity label. Uses BIO tagging: B-PER (beginning of person name), I-PER (inside person name), O (outside any entity). Modern NER uses transformer-based models fine-tuned on labeled data.
Entity Types
Standard types: Person, Organization, Location, Date, Money, Percentage. Domain-specific: Gene names (biomedical), Legal entities, Product names, Programming languages. Custom NER models can be trained for any entity type.
Applications
Information extraction from documents. Knowledge graph construction. Redacting personal information (PII detection). Enriching search with entity understanding. News analysis and event detection.