Beginner · NLP

Named Entity Recognition (NER)

Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.

TL;DR. An NLP task that identifies and classifies named entities like people, organizations, and locations in text.

Technical Definition

An NLP task that identifies and classifies named entities like people, organizations, and locations in text.

How it works

NER systems scan text and tag spans referring to real-world entities: Person, Organization, Location, Date, etc. Modern NER uses Transformer-based models fine-tuned on annotated text. It powers search engines, chatbots, and knowledge graph construction.

Related Concepts

• Transformer — An architecture that uses self-attention to process sequences in parallel, powering modern language models like GPT and BERT.
• Tokenization — The process of breaking text into smaller units (tokens) that language models can process as numerical inputs.
• BERT — A bidirectional Transformer model pre-trained on masked language modeling, revolutionizing NLP benchmarks across the board.