principles.fyi · the brain · concept

named entity recognition

Finding and labeling the names in text — people, places, companies, dates.

each token -> entity label (PERSON, LOC, ORG, ...) or none

Named entity recognition (NER) spots spans of text that name real things and tags them by type: person, location, organization, date, and so on. Unlike sequence classification, it's a per-token job — every token gets its own label — so it uses the encoder's individual contextual embeddings rather than just [CLS]. Context is essential here, since 'Washington' could be a person, a place, or an organization depending on the surrounding words.