Named Entity Recognition (NER)
An NLP task that identifies and classifies named entities in text into predefined categories such as person names, organizations, locations, dates, and monetary values.
Named entity recognition extracts structured information from unstructured text. Given a sentence like "Apple released the iPhone 16 in Cupertino on September 9, 2024," NER identifies "Apple" as an organization, "iPhone 16" as a product, "Cupertino" as a location, and "September 9, 2024" as a date. This transforms free-form text into queryable, structured data.
Traditional NER used conditional random fields and BiLSTM models trained on labeled datasets. Modern approaches leverage LLMs for zero-shot or few-shot entity extraction, which can handle custom entity types without retraining. You can prompt an LLM to extract "competitor mentions," "feature requests," or "pricing complaints" from customer feedback just by describing what to look for.
For growth teams, NER enables powerful automation: extracting company names and roles from signup forms for lead enrichment, identifying product mentions in social media for brand monitoring, parsing support tickets to route them to the right team, and structuring user-generated content for search and recommendation. The combination of LLM-based extraction with traditional NER for high-volume processing offers the best balance of flexibility and cost.
Related Terms
RAG (Retrieval-Augmented Generation)
A technique that grounds LLM responses in external data by retrieving relevant documents at query time and injecting them into the prompt context.
Embeddings
Dense vector representations of text, images, or other data that capture semantic meaning in a high-dimensional space, enabling similarity search and clustering.
Vector Database
A specialized database optimized for storing, indexing, and querying high-dimensional vector embeddings with sub-millisecond similarity search.
LLM (Large Language Model)
A neural network trained on massive text corpora that can generate, understand, and transform natural language for tasks like summarization, classification, and conversation.
Fine-Tuning
The process of further training a pre-trained LLM on a domain-specific dataset to specialize its behavior, style, or knowledge for a particular task.
Prompt Engineering
The practice of designing and iterating on LLM input instructions to reliably produce desired outputs for a specific task.