| 一个基于互信息的规则量化方法 |
| |
| 引用本文： | 高升,贾文举,王晓龙,姜亚学. 一个基于互信息的规则量化方法[J]. 计算机研究与发展, 2000, 37(8): 984-989 |
| |
| 作者姓名： | 高升 贾文举 王晓龙 姜亚学 |
| |
| 作者单位： | 1. 大庆石油学院计算机科学系,大庆,151400
2. 哈尔滨工业大学计算机科学与工程系,哈尔滨,150001 |
| |
| 摘 要： | 规则量化问题是基于规则与统计相结合的计算语言模型的关键性问题，首先描述了一个基于规则与统计相结合的计算语言模型，从而引出了规则结合度的概念，并提出一种基于互信息的规则量化方法，该方法既给出了一条规则的实用性的定量评价，又为基于规则与统计相结合的计算语言模型提供了一个重要的规则参量，通过实验指出该方法对系统规则集的筛选与计算语言模型中规则与统计结合机制的优化的重要指导意义。
|
| 关 键 词： | 互信息 规则结合度 规则量化 计算语言 |
A MUTUAL-INFORMATION-BASED APPROACH TO RULE QUANTIFICATION |
| |
| GAO Sheng,JIA Wen-Ju,JIANG Ya-Xue,WANG Xiao-Long. A MUTUAL-INFORMATION-BASED APPROACH TO RULE QUANTIFICATION[J]. Journal of Computer Research and Development, 2000, 37(8): 984-989 |
| |
| Authors: | GAO Sheng JIA Wen-Ju JIANG Ya-Xue WANG Xiao-Long |
| |
| Abstract: | The rule quantification problem is the key to a hybrid language model which integrates grammar rules into a statistical language model. This paper discusses a new type of hybrid language model, from which the concept of rule combination degree is derived, and then presents a mutual|information|based approach to rule quantification. The experiments show that this approach is a valuable guide for both the selection of system rule base and the combination mechanism of rule and statistic. |
| |
| Keywords: | language model phrase combination rule mutual information rule combination degree |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
