摘要
汉字的“字”与汉语的“词”单位不一致,给人脑和电脑的理解都带来困难。汉语另外有三种可能的文本“:汉字词式书写”文本“,纯拼音词式书写”文本和“拼音夹用汉字”文本“。拼音夹用汉字”文本最有可能成为走出汉语自动理解困境的最佳路径。
The unit of Chinese Characters is inconsistent with the unit of Chinese word ,which brings many difficulties to human and computers. Chinese text provides three possible methods： write the Chinese text word by word; write it by Chinese Phonetic Alphabet purely;write by ＂Chinese Phonetic Alphabet ＋Chinese Characters＂ ,in which the third method is the best way to free Chinese from the Predicament of automatic comprehension.
出处
《术语标准化与信息技术》
2006年第4期36-40,共5页
Terminology Standardization & Information Technology
关键词
语言信息处理
汉语
自动理解
词语切分
文本改革
linguistic information processing
Chinese
automatic comprehend
Chinese automatic segmentation
text reform
