摘要
目前中文文本自动校对的研究集中在词级和句法查错两方面,语义级查错仍是其中的薄弱环节。文章讨论了中文文本自动校对中的语义错误校对技术,综合使用了基于实例、基于统计和基于规则的搭配关系进行检查,提出统计和规则相结合的校对策略,既能检查局部语义限制,也能检查长距离的语义搭配,收到了较好的效果,也为中文自动校对的发展提供了新的思路。
The study of Automatic proofreading for Chinese Text focuses on Word-level and Syntactic checking errors at present.Semantic Errors Checking is still a weak point.This paper discusses technology of semantic errors checking in automatic proofreading for Chinese text,uses collocation relationship based on instances,statistics and rules to check er-rors,and proposes proofreading strategy combining statistical approach and rules.It can check both local semantic re-straints and remote semantic collocations.The strategy achieves satisfactory results and provides new thoughts for future development of automatic proofreading for Chinese Text.
出处
《计算机工程与应用》
CSCD
北大核心
2003年第12期115-118,共4页
Computer Engineering and Applications
关键词
中文文本自动校对
基于实例
语义相邻矩阵
语义共现矩阵
Automatic Proofreading for Chinese Text,Instance-based,Semantic Adjacent Matrix,Semantic Co-occurrence Matrix