Named-entity recognition (NER) (also known as entity identification and entity extraction) is a subtask of information extraction that seeks to locate and classify atomic elements in text into predefined categories such as the names of persons, organizations, locations, expressions of times, quantities, monetary values, percentages, etc.
Most research on NER systems has been structured as taking an unannotated block of text, such as this one:
- Jim bought 300 shares of Acme Corp. in 2006.
And producing an annotated block of text, such as this one:
Jim bought300 shares ofAcme Corp. in2006 .
In this example, the annotations have been done using so-called ENAMEX tags that were developed for the Message Understanding Conference in the 1990s.
State-of-the-art NER systems for English produce near-human performance. For example, the best system entering MUC-7 scored 93.39% of F-measure while human annotators scored 97.60% and 96.95%. These algorithms had roughly twice the error rate (6.61%) of human annotators (2.40% and 3.05%).
Read more about Named-entity Recognition: Approaches, Problem Domains, Named Entity Types, Current Challenges and Research, Available Technology, NER Evaluation Forums
Famous quotes containing the word recognition:
“By now, legions of tireless essayists and op-ed columnists have dressed feminists down for making such a fuss about entering the professions and earning equal pay that everyone’s attention has been distracted from the important contributions of mothers working at home. This judgment presumes, of course, that prior to the resurgence of feminism in the ‘70s, housewives and mothers enjoyed wide recognition and honor. This was not exactly the case.”
—Mary Kay Blakely (20th century)