Using data mining techniques and rough set theory for language modeling

被引：0

作者：

Chen, Yong ^{[1
,3
]}

Chan, Kwok-Ping ^{[2
,4
]}

机构：

[1] University of Hong Kong, 54th Research Institute of CTE, China, Fudan University

[2] Department of Computer Science, University of Hong Kong, Hong Kong, Pokfulam Road

[3] Department of Computer Science, University of Hong Kong

来源：

ACM Transactions on Asian Language Information Processing | 2007年 / 6卷 / 01期

关键词：

Chinese character recognizer; Postprocessing;

D O I：

10.1145/1227850.1227852

中图分类号：

学科分类号：

摘要：

In this article, we propose a new postprocessing strategy, word suggestion, based on a multiple word trigger-pair language model for Chinese character recognizers. With the word suggestion strategy, Chinese character recognizers may even achieve a recognition rate greater than the top-n candidate recognition rate. To construct the multiple word trigger-pair model, data mining techniques are used to alleviate the intensive computation problem. Furthermore, rough set theory is first used in the study to discover negatively correlated relationships between words in order to prevent introducing wrong words in the process of word suggestion. © 2007 ACM.

引用