中文自動分詞及人名識別技術(shù)研究.pdf

1、合肥工業(yè)大學(xué)碩士學(xué)位論文中文自動分詞及人名識別技術(shù)研究姓名：蔣才智申請學(xué)位級別：碩士專業(yè)：計算機軟件與理論指導(dǎo)教師：王浩2011-042 Research of Automatic Chinese segmentation and name recognition Abstract With the continuous development of national information technology and the pop

2、ularization of Internet, natural language understanding becomes a hot research field. As the first step in natural language understanding, automatic Chinese segmentation is more sophisticated and it determines the follow

3、-up processes. Chinese name is the most important component of unknown words, its existence is one of the most important factors which are influence the segmentation accuracy. Therefore, Chinese name recognition is a key

4、 technology in Chinese automatic segmentation. Currently, it is still unsatisfactory in processing on the result, its recognition quality still need to be enhanced in the further. This thesis will research Chinese autom

5、atic segmentation model and Chinese name identify problems, mainly work focused on: (1)A new dictionary mechanism named Dynamic four-character bidirectional dictionary mechanism is proposed. In this dictionary mechanism,

6、 we can reduce the mean frequency of visiting dictionary effectively. (2) In order to boost the precision of Chinese name recognition, we construct a Chinese name recognition model combining HowNet with Bayesian classifi

7、er. The basic idea is to locate and recognize the Chinese name roughly by Bayesian classifier, and then to fix this name by using HowNet. The model not only has the advantages of simple formula and ability to learn, but

8、also overcomes the extensive use of rules and the difficulty of boundary defining. Keywords: natural language understanding; Automatic Chinese segmentation; four-character dictionary; Chinese name recognition; Bayesian c