Fusion of Long Distance Dependency Features for Chinese Named Entity Recognition Based on Markov Logic Networks

摘要

For the issue that existing methods for Chinese Named Entity Recognition(NER) fail to consider the long-distance dependencies,which is common in the document.This paper,Fusion of long distance dependency,proposes a method for Chinese Named Entity Recognition( NER) based on Markov Logic Networks(MLNs),which comprehensively utilizes local,short distance dependency and long distance dependency features by taking advantage of first order logic to represent knowledge,and then integrates all the features into Markov Network for Chinese named entity recognition with the help of MLNs.Validity of proposed method is verified both in open domain and restricted domain,experimental result shows that proposed method has better effect.