基于键盘距离和依存分析的拼写纠错方法

吉林大学学报(理学版) ›› 2018, Vol. 56 ›› Issue (5): 1179-1186.

基于键盘距离和依存分析的拼写纠错方法

谢文慧^1, 易荣庆², 彭涛^1,3

1. 吉林大学计算机科学与技术学院, 长春 130012； 2. 国网吉林省电力有限公司, 长春 130022；3. 吉林大学符号计算与知识工程教育部重点实验室, 长春 130012

收稿日期:2017-11-10 出版日期:2018-09-26 发布日期:2018-11-22
通讯作者: 彭涛 E-mail:tpeng@jlu.edu.cn

Spelling Correction Method Based onKeyboard Distance and Dependency Parsing#br#

XIE Wenhui^1, YI Rongqing², PENG Tao^1,3

1. College of Computer Science and Technology, Jilin University, Changchun 130012, China;2. State Grid Jilin Electric Power Company, Changchun 130022, China;3. Key Laboratory of Symbol Computation and Knowledge Engineering for Ministry of Education,Jilin University, Changchun 130012, China

Received:2017-11-10 Online:2018-09-26 Published:2018-11-22

摘要/Abstract

摘要： 利用基于键盘距离和依存分析的拼写纠错模型, 解决文本输入过程中产生的非词错误. 通过综合考虑邻近权值、依存关系权值及词频三部分构造最终的拼写纠错模型, 并在Brown语料库、 Gutenberg语料库和Inaugural语料库上验证该模型. 实验结果表明, 该模型可有效进行非词纠错.

关键词: 键盘距离, 单词距离, 依存分析, SpellKD模型, 非词错误

Abstract: Using a spelling correction model based on keyboard distance and dependency parsing, the nonword errors generated in the process of text input were solved. The final spelling correction model was constructed by considering three parts: the proximity weight, the dependency weight and the word frequency. The model was validated in the Brown corpus, the Gutenberg corpus and the Inaugural corpus. The experimental results show that the model can be effective for nonword error correction.

Key words: keyboard distance, word distance, dependency parsing, , SpellKD model, nonword error

中图分类号:

TP391

谢文慧, 易荣庆, 彭涛. 基于键盘距离和依存分析的拼写纠错方法[J]. 吉林大学学报(理学版), 2018, 56(5): 1179-1186.

XIE Wenhui, YI Rongqing, PENG Tao. Spelling Correction Method Based onKeyboard Distance and Dependency Parsing#br#[J]. Journal of Jilin University Science Edition, 2018, 56(5): 1179-1186.