Named Entity Recognition
Learn how to perform named entity recognition using Python.
We'll cover the following...
Introduction
Named entity recognition (NER) is a text preprocessing technique that identifies and categorizes named entities in text, such as people, organizations, locations, dates, and other entities. By identifying and categorizing named entities in text, we can answer questions such as “who,” “what,” “when,” “where,” and “how” more accurately. Here are a few examples of common NER tags:
Common NER Tags
Short form | Full form | Meaning | Example |
GPE | Geopolitical entity | Represents a geopolitical entity (e.g., countries, cities) | “France” (She traveled to France.) |
ORG | Organization | Represents an organization (e.g., companies, institutions) | “Google” (She works at Google.) |
FAC | Facility | Represents a facility or building | “Eiffel Tower” (She visited the Eiffel Tower.) |
PERSON | Person | Represents a person | “John” (She met John.) |
NORP | Nationalities or religious or political groups | Represents nationalities, religious, or political groups | “American” (She is an American.) |
WORK_OF_ART | Work of art | Represents a work of art (e.g., books, songs, paintings) | “Mona Lisa” (She admired the Mona Lisa.) |
TIME | Time | Represents a point in time or a duration | “10 a.m.” (The meeting is at 10 a.m.) |
LANGUAGE | Language | Represents a language | “English” (She speaks English.) |
Application areas of NER include information retrieval, ...