摘要
教材文本相对于普通文本有其独特性。通过分析教材目录的特征，获取领域词汇的种子概念。通过分析教材正文中知识点的特征，提取出知识点的特征值，然后利用决策树C4．5算法对知识点类型进行识别，实现了教材文本的本体学习。
A course book text is different from other texts. The seed concept of the vocabulary in the field is to be obtained by making an analysis on the characteristic of the course book contents. Once the features of the element of knowledge points are extracted by analyzing, the decision tree C 4.5 method will be employed to identify the types of the knowledge point and the ontology learning on the text be achieved.
作者
特列克·巨马夏力甫
阿依兵·哈子太
Telek Zhumasharip, Ayben Kazitay （1 .Software College, Shandong University, Jinan 250101, China; 2.Nationalities Publishing House, Beijing 100013, China）
出处
《电脑知识与技术》
2011年第6期3986-3987,4008,共3页
Computer Knowledge and Technology
关键词
教材文本
目录
知识点
决策树
本体学习
course book text
vocabulary
knowledge point
decision tree
ontology learning
