摘要
藏文信息化发展至今已经取得了一定的成果,但存在的问题还有许多。藏文文本校对是实现藏文信息处理的基础,是藏文信息处理必不可少的工作。藏文文本校对的内容较广,方面较多,文中主要以藏文文本的词语校对作为研究的目标,通过使用最大匹配算法的思想在不进行分词的情况下对文本的词语作校对。文中对校对算法进行了叙述,并通过实验验证了该方法是可行性和校对效果。
The development of Tibetan informatization has achieved certain results so far,but there are still many problems.The proofreading of Tibetan texts is the basis for the realization of Tibetan information processing and is an indispensable task for Ti⁃betan information processing.The content of Tibetan text proofreading is relatively wide and there are many aspects.The main pur⁃pose of this paper is to use the proofreading of Tibetan texts as the research goal.By using the idea of maximum matching algorithm,the words of the text are proofed without participle.The proofreading algorithm is described in the paper,and the feasibility and proofreading effect of the method is verified by experiments.
作者
王福钊
周雁
WANG Fuzhao;ZHOU Yan(School of Information Science and Technology,Tibet University,Lhasa 850000;School of Computer,Beijing Institute of Technology,Zhuhai,Zhuhai 519000)
出处
《计算机与数字工程》
2021年第7期1433-1436,共4页
Computer & Digital Engineering
关键词
藏文
文本校对
词语校对
最大匹配
算法设计
Tibetan
text proofreading
proofreading
maximum matching
algorithm design
