Named entity recognition
Named entity recognition is a natural-language-processing task that identifies textual mentions of entities and classifies them into categories such as people, places, organizations, or dates.
Natural Language Processing in Action, Second Edition
Named entity recognition identifies spans of text that refer to entities such as people, places, organizations, dates, or locations and assigns them entity categories.
- How it is used
- Extracts entity mentions as the first stage of pipelines that convert text into knowledge graphs and grounded language applications.
- How deep it goes
- Explains spans, categories, pattern matching, neural architectures, ambiguity, and spaCy inspection, but defers model construction.
- Examples
- Uses a Timnit Gebru Wikipedia article, spaCy entity output, and ambiguous examples including New York and Washington.
- What you can do after
- Apply NER via spaCy, inspect extracted spans and categories, and prepare entities for relation extraction or knowledge-graph construction.
Read how Natural Language Processing in Action, Second Edition explains named entity recognition →
Knowledge Graphs and LLMs in Action
Named entity recognition is the natural-language-processing technique of identifying mentions of named entities in text and assigning them to predefined categories.
- How it is used
- Supports knowledge-graph construction, search, compliance, information management, and domain-specific analysis by structuring mentions in raw text.
- How deep it goes
- Explains category design, prompt-based extraction, structured outputs, and offsets, while stopping short of resolving entity identity or meaning.
- Examples
- Uses Rockefeller’s diary topics, biomedical Zika sentences, SNOMED categories, JSON records, and character-offset extraction.
- What you can do after
- Apply it via custom models or LLM prompts to extract domain-specific entities as validated structured records for downstream processing.
Read how Knowledge Graphs and LLMs in Action explains named entity recognition →
Graph Algorithms for Data Science
Named entity recognition is a natural language processing task that identifies and classifies textual mentions of entities into predefined categories.
- How it is used
- Identifies entity mentions in unstructured text as a step toward extracting structured information and constructing graphs.
- How deep it goes
- Defines NER, explains domain-dependent categories, and demonstrates labeled output without detailing model internals.
- Examples
- Uses Google, YouTube, and Eric Schmidt as labeled entities, visualized with displaCy.
- What you can do after
- Apply NER by labeling domain-relevant people, organizations, locations, dates, or specialized biomedical entities.
Read how Graph Algorithms for Data Science explains named entity recognition →
Machine Learning System Design
Named entity recognition is a natural-language-processing technique that identifies and classifies mentions of entities in text.
- How it is used
- Uses knowledge-base lookups to address missed customer-important entities when model retraining is impractical.
- How deep it goes
- Explains knowledge-base input augmentation and contrasts it with output overrides, without detailing entity-recognition model training.
- Examples
- Uses a customer-facing system that checks a knowledge base before inference and accepts entries added by nontechnical staff.
- What you can do after
- Apply knowledge-base hints to correct missed entities without retraining the model.
Read how Machine Learning System Design explains named entity recognition →
Related concepts
- named entityproduces · A named entity is a textual mention of a specific, identifiable person, place, organization, date, or other entity that can be categorized.
- disambiguationcontrasts with · Disambiguation is the process of resolving ambiguity by selecting the intended interpretation, entity, or goal among plausible alternatives.
- classifierkind of · A classifier is a predictive computational model that assigns inputs to one or more discrete classes or categories.
- information extractionpart of · Information extraction is the computational process of identifying specified facts, entities, fields, or relationships in input data and producing structured information.
- structured extractionpart of · Structured extraction is the process of identifying specified information in source content and representing it as organized data in a defined structure.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.