摘要
汉语分词是汉语言计算机处理的一项不可缺少的工作。使用自动分词知识可以进一步提高自动切分精度,满足高标准的需求。本文在[1][2][3]的研究基础上,介绍了一些行之有效的自动分词知识。根据对48,092个汉字的语言材料统计结果表明(统计材料分社会科学和自然科学两部分),这些自动分词知识可以处理90％左右的歧义切分字段。
Chinese words segmentation is a important work for Chinese language, processing with computer. Knowledge of Chinese words automatic segmentation can raise the precision of automatic segmentation, and it can satisfy high precision requirements. This paper introduces some efficiient knowledge of words automatic segmenuion based on the research of [1],[2],[3],Those knowledge can process about 90% polysemous segmentation phases, the result is from the statistics of two language which there are 48,092 Chinese characters.
出处
《中文信息学报》
CSCD
1990年第2期29-41,共13页
Journal of Chinese Information Processing
