文本数据挖掘技术对速记教学及语料库建设的启示——以松下幸之助演讲数据分析为样例  

The Enlightment of Text Data Mining to Stenography Teaching and Its Corpus Construction——Taking the Data Analysis of Konosuke Matsushita's Speeches as an Example

作　　者：闵阅[1] 老青[2] 丁潇君[3] 

机构地区：[1]高等教育出版社外语与国际汉语出版事业部,北京100029 [2]北京青年政治学院英语系,北京100102 [3]北京工业大学经管学院,北京100124

出　　处：《韶关学院学报》2015年第7期170-174,共5页Journal of Shaoguan University

基　　金：2015年北京市高职学生培养--高端技术技能人才培养模式改革子项目"旅游英语专业实践教学研究与实训资源建设"(PXM2015-014208-000023)

摘　　要：基于文本数据挖掘技术,探讨在速记教学设计中如何培养职业速记人员利用文本数据挖掘技术发现潜在的、有用的知识,以更加有效地开展速记前的信息储备工作。速记笔记符号识别语料库能够解决速记中笔记产出的受阻情况,提升速记笔记记录源信息的质量。＇Text Data Mining＇ （TDM） is a kind of technology for analyzing a large amount of text data by dozens of measures, with which people could find out patterns and laws, as well as gain useful knowledge and information. Also, we are discussing how to cultivate such ability in the design of shorthand teaching so that professional stenographers could utilize TDM to discover the underlying and valuable knowledge in order to make a better and more effective preparation before taking shorthand. And we think that notation recognition corpus based on TDM for shorthand purpose could be helpful for notation-output and improve quality of shorthand.

关 键 词：文本数据 挖掘技术 速记教学 语料库建设 

分 类 号：H026.1[语言文字—语言学]