首页 | 本学科首页   官方微博 | 高级检索  
     

Combining Trigram and Automatic Weight Distribution in Chinese Spelling Error Correction
作者姓名:李建华  王晓龙
作者单位:SchoolofComputerScienceandTechnology,HarbinInstituteofTechnology,Harbin150001;P.R.China
基金项目:This research is supported by the National Natural Science Foundation of China under Grant No.69973015.
摘    要:The researches on spelling correction aiming at detecting errors in texts tend to focus on context-sensitive spelling error correction,which is more difficult than traditional isolated-word error correction,A novel and efficient algorithm for the system of Chinese spelling error correction,CInsunSpell,is presented.In this system,the work of correction includes two parts:checking phase and correcting phase,At the first phase ,a Trigram algorithm within one fixed-size window is designed to locate potential errors in local area.The second phase employs a new method of automatically and dynamically distributing weights among the characters in the confusion set as well as in the Bayesian language model.The tactics used above exhibits good performances.

关 键 词:中文信息处理  拼音错误矫正  Bayesian语言模型
收稿时间:16 August 2006

Combining trigram and automatic weight distribution in Chinese spelling error correction
Jianhua Li,Xiaolong Wang.Combining Trigram and Automatic Weight Distribution in Chinese Spelling Error Correction[J].Journal of Computer Science and Technology,2002,17(6):0-0.
Authors:Jianhua Li  Xiaolong Wang
Affiliation:(1) School of Computer Science and Technology, Harbin Institute of Technology, 150001 Harbin, P.R. China
Abstract:The researches on spelling correction aiming at detecting errors in texts tend to focus on context-sensitive spelling error correction, which is more difficult than traditional isolated-word error correction. A novel and efficient algorithm for the system of Chinese spelling error correction, CInsunSpell, is presented. In this system, the work of correction includes two parts: checking phase and correcting phase. At the first phase, a Trigram algorithm within one fixed-size window is designed to locate potential errors in local area. The second phase employs a new method of automatically and dynamically distributing weights among the characters in the confusion set as well as in the Bayesian language model. The tactics used above exhibits good performances.
Keywords:spelling error correction  language model  edit distance  weight distribution
本文献已被 CNKI 维普 万方数据 SpringerLink 等数据库收录!
点击此处可从《计算机科学技术学报》浏览原始摘要信息
点击此处可从《计算机科学技术学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号