Named Entity Recognition (NER)
Definition
NER recognizes and labels names and other named information in texts.
The recognition and typing of text spans that designate, for example, persons, organizations, places, or products.
Simply explained
A program marks, for example, persons, companies, and places in the text and classifies them.
Why it matters in practice
Helps realistically assess model quality, limits, and technical decisions.
Example from business
Suppliers, locations, and dates are marked from emails for verification.
Limits and pitfalls
- Do not equate NER with unique identification or fail to train domain-specific entity types.
Origin & history
NER is a classic information extraction task; CoNLL shared tasks established common datasets and evaluation protocols.
Use in mid-sized companies
- Possible example: Suppliers, locations, and dates are marked from emails for verification.
Frequently asked questions
What does named entity recognition (NER) mean?
The recognition and typing of text spans that designate, for example, persons, organizations, places, or products.
Which mistakes should be avoided?
Do not equate NER with unique identification or fail to train domain-specific entity types.
Sources
Source checked on 10.10.2026. Editorial application examples are hypothetical; no proof of real customer results.
Editorially reviewed on: