Named entity recognition

摘要: The idea of automatic extraction of important information from text documents comes from the time of first steps in the natural language processing. Its importance rapidly grows with the rise of the digital news, social media, blogging, etc. The amount of information is overwhelming and information extraction can help to manage it.Named entity recognition is a critical subtask of information extraction. It tries to recognize and classify multiword expressions with special meaning, eg persons, organizations, locations, dates, etc. In many cases, these expressions hold the key information of the document. This information has many uses. It can be used for better organization of documents, filtering of important documents, or simply as an input for other natural language processing tasks such as machine translation, question answering, or summarization.