摘要
针对《现代汉语语法信息词典》不能准确描述真实语料的缺陷,设计了构建概率型语法信息词典名词库的存储结构,提出利用统计模型概率化词语属性的方法,建立完整的名词概率化语法信息词典,设计并实现了概率型语法词典应用于语法词典自纠错的算法,实验证明其具有自纠错能力。
In order to overcome the deficiency that the＂grammatical knowledge-base of contemporary Chinese＂（GKB） cannot describe the real corpus,a storage structure to store the probability grammar knowledge-base of nouns is designed.In this paper,a method using statistical model is proposed to establish nouns probability grammar dictionary.Finally,the error correction method making use of nouns probability grammar knowledge-base is designed and implemented and the experimental result proves its ability on correction of itself.
出处
《北京信息科技大学学报（自然科学版）》
2011年第6期57-61,共5页
Journal of Beijing Information Science and Technology University
基金
国家自然科学基金资助项目(60873013
61070119)
北京大学计算语言学教育部重点实验室开放课题基金项目(KLCL-1005)
北京市属市管高等学校人才强教计划资助项目(PHR201007131)
关键词
语法信息词典
概率化
查错
纠错
grammatical knowledge-base of contemporary Chinese
probability
error-detecting
correction
