Abstract
Named entity recognition (NER), it is a technique in natural language processing (NLP) that aims to identify and classify entities. The goal of NER is to extract data generated from unstructured text so that machines can understand and classify entities useful for a variety of applications such as text recognition, typing, creating knowledge maps, tests, and knowledge graphs. This article examines the principles, methods, and applications of the NER model. NER is also known as entity extraction, fragmentation and recognition. It is used in many areas of artificial intelligence (AI), including machine learning (ML), deep learning, and neural networks. NER is a key component of NLP systems such as chat bots, sentiment analysis tools, and search engines. It is used in healthcare, finance, human resources (HR), customer support, higher education, and social analytics. NER identifies, classifies and extracts the most important information from raw documents without the need for time-consuming manual searches. It is particularly useful for extracting important data from large files because it can speed up the extraction process. NER models help advance artificial intelligence as they improve their ability to analyze important data. These systems have improved their ability to understand AI language in areas such as content analysis and translation, as well as the ability of AI systems to analyze text. The NER grammar uses algorithms based on NLP models and prediction models. These algorithms are trained on data that people save with predefined names such as people, places, organizations, expressions, percentages, financial values, etc. Categories are defined by abbreviations; e.g. LOC for location, PER for people, ORG for organization.