Named entity recognition (NER) is a sub-task of information extraction (IE) that seeks out and categorizes specified entities in a body or bodies of texts. NER is also known simply as entity identification, entity chunking and entity extraction. NER is used in many fields in artificial intelligence (AI) including natural language processing (NLP) and machine learning.
Information extraction depends on NER to find targeted information, using models that function based on grammar or statistical models. NER recognizes entities first as one of several categories such as people, locations, organizations, expressions, percentages and monetary values. Categories are abbreviated: location (LOC), persons (PER) and organizations (ORG), etc. Once the information category is recognized, an information extraction utility extracts the named entity’s related information and constructs a machine-readable document from it that other tools can further process to extract meaning.
As with many difficult tasks in AI, NER challenges are put forth to the development community to encourage development of solutions. Message Understanding Conference (MUC) is one such challenge. Comparably, humans scored a 97.60 percent and 96.95 percent accuracy while the best IE system scored 93.39 percent.