RESEARCH ON ME-BASED CHINESE NER MODEL
This paper presents a hybrid pattern for Chinese Name Entity Recognition based on Maximum Entropy model. Firstly, Maximum Entropy model is an outstanding statistical model for its good integration of various constraints and its compatibility to Chinese Named Entity Recognition. Secondly, local features and global features are integrated in the hybrid model to get high performance. Thirdly, in order to reduce the searching space and improve the processing efficiency, heuristic human knowledge is introduced into the model, which could increase the recognition performance significantly. From the experimental results on Peoples Daily corpus, it can be observed that the hybrid model is an effective pattern to combine statistical model and heuristic human knowledge.
Named entity recognition Mazimum entropy model Local feature Global feature Heuristic human knowledge
YUE-JIE ZHANG TAO ZHANG
Department of Computer Science and Engineering, Shanghai Key Laboratory of Intelligent Information P School of Information Management and Engineering, Shanghai University of Finance and Economics, Shan
国际会议
2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)
昆明
英文
2597-2602
2008-07-12（万方平台首次上网日期，不代表论文的发表时间）