Natural Language Processing (NLP) - Named Entity Recognition (NER)

Named Entity Recognition (NER) is a subtask of information extraction that identifies named entities in text such as persons, organizations, locations, medical codes, time expressions, quantities, monetary values, percentages, etc.

Key Concepts

Named Entities: These are words or phrases that refer to specific entities. For example, "Apple Inc." is a named entity.
NER Systems: These systems are designed to detect and classify named entities in text.

NER in Practice

Here are some practical examples of NER:

Identifying People: "John Doe" is a named entity referring to a person.
Identifying Organizations: "Google Inc." is a named entity referring to a company.
Identifying Locations: "New York" is a named entity referring to a city.

Techniques

NER systems can be based on various techniques:

Rule-Based Systems: These systems use a set of predefined rules to identify named entities.
Statistical Models: These models use statistical methods to predict the presence of named entities.
Machine Learning Models: These models learn from labeled data to identify named entities.

Tools

There are several tools available for NER:

spaCy: An open-source natural language processing library.
Stanford CoreNLP: A suite of natural language processing tools.
NLTK: A leading platform for building Python programs to work with human language data.

More Information

For more information on NLP and NER, you can visit our NLP Basics tutorial.

Learning Resources