The Role of Named Entity Recognition (NER): Survey

Named Entity Recognition (NER) is an Information Extraction (IE) building block. Though the information extraction process has been automated using various techniques to find and extract relevant information from unstructured documents, the discovery of targeted knowledge still poses many research difficulties because of Web data's variability and lack of structure. NER, a subtask of IE, came to exist to smooth such difficulty. It deals with finding the proper names (named entities), such as a person's name, country, location, organization, dates, and event in a document. It categorises them as predetermined labels, an initial step in IE tasks. This survey paper presents the roles and importance of NER to IE from the perspective of different algorithms and application area domains. Additionally, it summarizes how researchers implemented NER in particular application areas like finance, medicine, defense, business, food science, archeology, etc. It also outlines the three NER sequence labeling algorithms types: feature-based, neural network-based, and rule-based. Finally, the state-of-the-art and evaluation metrics of NER were presented.