A Pre-Identification Method for Chinese Named Entity Recognition

In this paper, a pre-identification method for Chinese named entity recognition is proposed. Internal information of entity name like family name, first name in person name, feature word in place name and organization name do not needed. Through entity name guessing based on context keywords, pre-identification is realized. Definition of bidirectional potential entity name recognition, rough confirmation of potential entity name, segmentation word is proposed. To solve the possible ambiguity in entity name identification, the degree of segmentation and conjunction is presented as well as cascade recognition and final confirmation. Combining with this pre-processing method, performance will be improved by using internal information of entity name. Experiment proves that the method have a special advantage in recognition special entity name, ambiguity name and irregular name. In this paper, Chinese person name is taken as an example for entity name recognition. Nevertheless, the method is not limit to person name recognition but also a pre-identification method for other entity name.