报告题目：KnowEdu: A System to Construct Knowledge Graph for Education

论文出处：Access 2018

作者：PENGHE CHEN¹, YU LU², VINCENT W. ZHENG³, XIYANG CHEN¹, AND BODA YANG¹

单位：¹Advanced Innovation Center for Future Education, Beijing Normal University, Beijing 100875,China

²Faculty of Education, School of Educational Technology, Beijing Normal University, Beijing 100875,China

³Advanced Digital Sciences Center, Singapore 138602 

报告人：陈露

报告时间：2022年10月17日 

报告地点：贵州大学北校区博学楼624室

报告内容摘要：Motivated by the vast applications of knowledge graph and the increasing demand ineducation domain, we propose a system, called KnowEdu, to automatically construct knowledge graphfor education. By leveraging on heterogeneous data (e.g., pedagogical data and learning assessment data)from the education domain, this system first extracts the concepts of subjects or courses and then identifiesthe educational relations between the concepts. More specifically, it adopts the neural sequence labelingalgorithm on pedagogical data to extract instructional concepts and employs probabilistic association rulemining on learning assessment data to identify the relations with educational significance. We detail all theabovementioned efforts through an exemplary case of constructing a demonstrative knowledge graph formathematics, where the instructional concepts and their prerequisite relations are derived from curriculumstandards and concept-based performance data of students. Evaluation results show that the F1 score forconcept extraction exceeds 0.70, and for relation identification, the area under the curve and mean averageprecision achieve 0.95 and 0.87, respectively.