What is NER (Named Entity Recognition)?
NER (Named Entity Recognition) identifies and classifies named entities in text—people, organizations, locations, dates, monetary values, and more. It's a foundational NLP technique for extracting structured data from unstructured documents.
Why It Matters
Contracts mention parties, dates, and amounts scattered throughout. NER automatically extracts these entities, enabling structured queries like "show all contracts expiring in Q1" without manual data entry. It's also essential for PII detection.
NER Example
# Input text
"Apple Inc. signed a $50M contract with Acme Corp on January 15, 2024."
# Extracted entities
ORG: Apple Inc., Acme Corp
MONEY: $50M
DATE: January 15, 2024
Common Entity Types
- • PERSON — Names of people
- • ORG — Companies, agencies, institutions
- • GPE — Countries, cities, states
- • DATE — Absolute and relative dates
- • MONEY — Monetary values
- • PRODUCT — Products, services