Named Entity Recognition (NER)

Executive Definition: Named Entity Recognition (NER) — A natural language processing (NLP) technique that identifies and classifies key entities in unstructured text into predefined categories.

NER automatically detects entities such as people, organizations, locations, dates, and monetary values within a text. It is a foundational tool for data extraction, content categorization, and transforming unstructured documents into structured information for downstream analysis.

Frequently Asked Questions

What types of entities does NER extract?

Standard NER extracts names, organizations, locations, dates, monetary values, and quantities. Custom NER models can extract domain-specific terms, such as medical conditions or product serial numbers.

How is NER implemented?

NER can be implemented using traditional statistical models (like CRFs), deep learning architectures (like BiLSTM-CRF or BERT-based models), or zero-shot extraction via Large Language Models (LLMs).

How does NER differ from text classification?

Text classification categorizes an entire document under a single label. NER identifies and categorizes specific substrings (entities) within the text.