Named Entity Recognition (NER) is a subtask of information extraction in Natural Language Processing (NLP) that identifies and categorizes specific entities in a text into predefined classes. These classes can be names of people, organizations, locations, expressions of times, quantities, monetary values, and more.
You can think of NER as a smart highlighter. When you’re reading a document and use a highlighter to mark the names of people, places, or dates, you’re performing a task similar to NER. The difference is that NER is done by a machine and can process large amounts of text quickly.
Here’s a more detailed explanation: NER involves locating and classifying named entities in text into predefined categories such as the names of persons, organizations, locations, expressions of times, percentages, etc. For instance, in the sentence “Apple Inc. was established in April 1976 by Steve Jobs, Steve Wozniak and Ronald Wayne.”, an NER system would recognize “Apple Inc.” as an organization, “April 1976” as a date, and “Steve Jobs”, “Steve Wozniak”, and “Ronald Wayne” as persons.
NER is used in many fields like computational linguistics, data mining, and knowledge management to structure and categorize large amounts of data. Applications of NER include machine translation, question answering, news article classification, and many more. It’s a key component in chatbots and voice assistants for understanding the context in human communication.
« Back to Glossary Index