Abstract: With the increase in availability of data, extraction of useful information from this data has become most important activity across all domains. When the data is available as documents written in natural language, information extraction becomes more challenging. Named Entity recognition (NER) is a technique used extensively for automatic extraction of useful information from unstructured natural language document collections. Used both, for web applications as well as stand-alone systems, NER is considered as one of the major step in Natural Language Processing (NLP) for analysis of text. This paper discusses basics of NER, various algorithms used for NER and major applications and challenges in the field of NER.

Keywords: Named Entity Recognition, Information Extraction, Natural Language Processing, Part of Speech.