This paper provides a comprehensive review of deep learning techniques for Named Entity Recognition (NER). NER is the task of identifying mentions of predefined semantic types such as person, location, and organization in text. Early NER systems relied on hand-crafted rules and domain-specific features, but recent advancements in deep learning have significantly improved performance. The paper introduces NER resources, including tagged corpora and off-the-shelf tools, and categorizes existing works based on distributed representations for input, context encoder, and tag decoder. It surveys representative methods for new NER problem settings and applications, and discusses challenges and future directions. The contributions of the survey include a detailed review of deep learning techniques, a new taxonomy for organizing DL-based NER approaches, and a discussion of the most recent advancements and applications.This paper provides a comprehensive review of deep learning techniques for Named Entity Recognition (NER). NER is the task of identifying mentions of predefined semantic types such as person, location, and organization in text. Early NER systems relied on hand-crafted rules and domain-specific features, but recent advancements in deep learning have significantly improved performance. The paper introduces NER resources, including tagged corpora and off-the-shelf tools, and categorizes existing works based on distributed representations for input, context encoder, and tag decoder. It surveys representative methods for new NER problem settings and applications, and discusses challenges and future directions. The contributions of the survey include a detailed review of deep learning techniques, a new taxonomy for organizing DL-based NER approaches, and a discussion of the most recent advancements and applications.