英文摘要 |
As the prevailing of e-publish, users can only choose those contents they need. Therefore, the customized-publish plays an important role in e-publish. According to this mechanism, users can search their favorite content. However, due to the lack of the interactive ability, users may spend much time but not get those contents they want. The way of understanding and representation what users’ want is the key factor in deciding the accuracy of response. The utilization of natural language is the best way to represent the thinking of human completely. However, there are still some problems for computers to understand natural language. In Chinese language there are two difficulties. First, as the Chinese language has no space to segment the lexical entry, the segmentation method of Chinese is more difficult than English. Second, the lack of complete grammar in Chinese language makes parser more difficult and complicated. These difficulties should be overcome by building a Chinese interactive feedback system. in this paper, a method to parse the Chinese language is proposed to use particular lexical database according to the application to improve the response time and accuracy. Therefore, a customized e-publish system can be built by this methods. |