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 more.
How It Works
NER models analyze text token by token, assigning each token a label: 'B-PER' (beginning of person name), 'I-ORG' (inside organization name), 'O' (outside any entity), etc. Modern NER uses transformer-based models fine-tuned on labeled datasets.
Applications
Information extraction from documents, building knowledge graphs, search engine entity linking, content recommendation, compliance monitoring (detecting PII), and medical record analysis.
Tools
spaCy (fast, production-ready), Hugging Face token classification models, Stanford NER, and LLM-based extraction (prompting an LLM to extract entities in structured format).