| 基于统计的藏文音节联想输入 |
| |
| 引用本文： | 多杰卓玛.基于统计的藏文音节联想输入[J].湛江师范学院学报,2008,29(3):96-100. |
| |
| 作者姓名： | 多杰卓玛 |
| |
| 作者单位： | 西北民族大学中国民族信息技术研究院,甘肃,兰州,730030 |
| |
| 摘 要： | 就藏文输入法而言，字符是最小的输入单位，然而音节则是最基本的输入单位．该文阐述了藏文音节的结构特点并分析了藏文音节内的前加字与基字、后加字、又后加字的关联关系，并对50M藏文语料的6709466音节做了各成分间的频率统计．用关联关系建立了字丁之间的简单联想输入模式．提出了藏文音节的三种联想输入方式——前加字联想方式、基字联想方式、基字位联想方式．
|
| 关 键 词： | 音节 统计 关联 联想输入 |
Statistic-Based Association Input Method For Tibetan |
| |
| DUO JIE Zhuo-ma.Statistic-Based Association Input Method For Tibetan[J].Journal of Zhanjiang Normal College,2008,29(3):96-100. |
| |
| Authors: | DUO JIE Zhuo-ma |
| |
| Institution: | DUO JIE Zhuo-ma (Institute of Information Technology, Northwest Minorities University, Gansu Lanzhou 730030,China) |
| |
| Abstract: | Characters is the smallest input unit while syllable is the basic unit for Tibetan input. This paper described the characteristics of syllable structure and analyzed the associated relation of prefixes and root, suffix, farther suffix. Their frequencies in syllable are obtained from a 50M Tibetan corpus with 6709466 syllables. Association input mode is established with associated relation between characters. Three types of association input mode which are suffix association, root association and root location association, are proposed. |
| |
| Keywords: | syllable statistic relevancy association input |
| 本文献已被 维普 万方数据 等数据库收录！ |
