KOREAN NAMED ENTITIES RECOGNITION METHOD BASED ON MAXIMUM ENTROPY MODEL AND NEURAL NETWORK MODEL

摘要

The invention belongs to the technical field of named entities recognition, and discloses a Korean named entities recognition method on the basis of a maximum entropy model and a neural network model. The method comprises: building a prefix tree dictionary, when any one combined noun template is matched with any one proper noun template in an input sentence, it is recognized as a target word; obtaining the target word in a target word selection module, searching the target word in an entity dictionary, and when only one subclass is matched, the subclass serves as a tag of the target word; adopting the maximum entropy model, and utilizing various linguistics information; constructing a feedforward neural network model; and grouping adjacency words into an entity tag through a template selection rule. All data used in the method is extracted in a training corpus with tags and a field-independent entity dictionary, the data is very easily migrated into other application fields, and the performance cannot be reduced obviously.