NLP Named Entity Recognition (NER)

Named Entity Recognition (NER) is a fundamental task in Natural Language Processing (NLP) that involves identifying and classifying named entities in text into predefined categories such as person names, organizations, locations, medical codes, time expressions, quantities, monetary values, percentages, etc.

What is NER?

NER is used in various applications like information extraction, sentiment analysis, machine translation, and question answering. It helps in understanding the context and semantics of the text.

How does NER work?

NER systems typically use machine learning algorithms to predict the tags for each token in the text. The tags can be pre-defined or learned from annotated data.

Examples

Here are some examples of NER in action:

• "Apple Inc." is recognized as an [ORGANIZATION].
• "New York" is recognized as a [LOCATION].
• "2023" is recognized as a [DATE].

Resources

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

Image

Here is an example of a named entity in a sentence: