| 基于混合语言模型的中文智能输入技术 |
| |
| 引用本文： | 章森,刘磊,刁麓弘.基于混合语言模型的中文智能输入技术[J].北京工业大学学报,2007,33(9):997-1001. |
| |
| 作者姓名： | 章森 刘磊 刁麓弘 |
| |
| 作者单位： | 北京工业大学,应用数理学院,北京,100022;北京工业大学,应用数理学院,北京,100022;北京工业大学,应用数理学院,北京,100022 |
| |
| 摘 要： | 分析了中文智能输入技术的研究现状和存在的问题,提出了基于混合n-gram的中文智能输入技术,给出了系统实现的架构,研究了混合2-gram模型的有关问题以及字词网格的求解算法,讨论了自动预测与系统学习功能的实现.测试结果表明拼音到汉字自动转换正确率达到了92.1%,基本实现了预期目标.
|
| 关 键 词： | 中文智能输入 n-gram语言模型 Markov模型 字词网格 用户行为 |
| 文章编号： | 0254-0037（2007）09-0997-05 |
| 修稿时间： | 2006-08-22 |
Chinese Intelligent Input Method based on Hybrid Language Model |
| |
| ZHANG Sen,LIU Lei,DIAO Lu-hong.Chinese Intelligent Input Method based on Hybrid Language Model[J].Journal of Beijing Polytechnic University,2007,33(9):997-1001. |
| |
| Authors: | ZHANG Sen LIU Lei DIAO Lu-hong |
| |
| Affiliation: | College of Applied Sciences, Beijing University of Technology, Beijing 100022, China |
| |
| Abstract: | First,the recent advances of Chinese intelligent input technology were briefly discussed and the principles and shortcomings were analyzed,then the Chinese intelligent input approach based on hybrid lan- guage model was proposed and the implementation of the main architecture was studied,after that,the relat- ed problems with hybrid language model and the algorithms to solve the word lattice were investigated,at last,the automatic prediction algorithm and the machine learning technology used in Chinese intelligent input systems were discussed;the experiment results based on the prototype system showed that the correct conver- sion rate from Pinyin to Chinese characters reached 92.1%,which meets the designed goals. |
| |
| Keywords: | chinese intelligent input n-gram language model markov model word lattice user's action |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
