大数据 ›› 2020, Vol. 6 ›› Issue (6): 26-39.doi: 10.11959/j.issn.2096-0271.2020052

• 专题:教育大数据 • 上一篇    

知识主题间先序关系挖掘

麻珂欣1,2,魏笔凡1,2,马杰1,2,刘均1,2,黄毅3,胡珉3,冯俊兰3   

  1. 1 西安交通大学计算机科学与技术学院,陕西 西安 710049
    2 陕西省天地网技术重点实验室,陕西 西安 710049
    3 中国移动研究院,北京 100032
  • 出版日期:2020-11-15 发布日期:2020-12-12
  • 作者简介:麻珂欣(1995- ),女,西安交通大学计算机科学与技术学院硕士生,主要研究方向为先序关系抽取|魏笔凡(1977- ),男,博士,西安交通大学计算机科学与技术学院高级工程师,主要研究方向为Web信息抽取、教育知识图谱构建及应用|马杰(1993- ),男,西安交通大学计算机科学与技术学院博士生,主要研究方向为知识图谱、机器学习、文本挖掘|刘均(1973- ),男,博士,西安交通大学计算机科学与技术学院教授,主要研究方向为自然语言处理、计算机视觉、智慧教育|黄毅(1989- ),男,中国移动研究院研究员,主要研究方向为自然语言处理和人机对话|胡珉(1981- ),男,中国移动研究院主任研究员,主要研究方向为信息检索和知识库|冯俊兰(1974- ),女,博士,中国移动研究院首席科学家,主要研究方向为语音识别、语言理解和数据挖掘
  • 基金资助:
    国家重点研发计划基金资助项目(2017YFB1401300);国家重点研发计划基金资助项目(2017YFB1401302);国家自然科学基金资助项目(61672419);国家自然科学基金资助项目(61672418);国家自然科学基金资助项目(61532015);国家自然科学基金资助项目(6193700);“人工智能”教育部-中国移动建设资助项目(MCM20190701);中国工程院咨询研究资助项目“基于MOOC中国的‘一带一路’人才培养的线上线下混合教学支撑信息化平台与服务体系”;国家自然科学基金创新研究群体资助项目(61721002);教育部创新团队资助项目(IRT_17R86);中国工程科技知识中心资助项目

Mining prerequisite relations among learning objects

Kexin MA1,2,Bifan WEI1,2,Jie MA1,2,Jun LIU1,2,Yi HUANG3,Min HU3,Junlan FENG3   

  1. 1 School of Computer Science and Technology,Xi’an Jiaotong University,Xi’an 710049,China
    2 Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Technology R&D,Xi’an 710049,China
    3 China Mobile Research,Beijing 100032,China
  • Online:2020-11-15 Published:2020-12-12
  • Supported by:
    National Key Research and Development Program of China(2017YFB1401300);National Key Research and Development Program of China(2017YFB1401302);The National Natural Science Foundation of China(61672419);The National Natural Science Foundation of China(61672418);The National Natural Science Foundation of China(61532015);The National Natural Science Foundation of China(6193700);MoE-CMCC “Artificial Intelligence” Project(MCM20190701);The Consulting Research Project of Chinese Academy of Engineering “The Online and Offline Mixed Educational Service System for ‘The Belt and Road’ Training in MOOC China”;Innovative Research Group of the National Natural Science Foundation of China(61721002);Innovation Research Team of Ministry of Education(IRT_17R86);Project of China Knowledge Centre for Engineering Science and Technology

摘要:

先序关系指知识主题之间学习的先后依赖关系。已有的先序关系挖掘方法大多是流线型的方式,易导致错误累计,且严重依赖可能导致错误先序关系的超链接。为了解决以上问题,先对知识主题间的先序关系进行统计分析,发现了先序关系的不对称性特征;接着提出从文本中挖掘知识主题间的先序关系的端到端先序关系挖掘模型。该模型基于文本中抽取出的术语间上下位关系,计算知识主题的相关术语集间先序关系的不对称性,进而预测知识主题间的先序关系。实验结果表明,该方法具有较优的先序关系抽取性能。

关键词: 先序关系, 不对称性, 端到端模型

Abstract:

Prerequisite relation refers to the learning dependency between learning objects.Most previous works mined prerequisite relations in a pipelined way and heavily relied on hyperlinks,which lead to the accumulation of errors.To address these issues,prerequisite relations among knowledge topics were analyzed,and the asymmetry feature of prerequisite relation was found out.An end-to-end prerequisite relation model for mining prerequisite relations from texts was proposed.Based on the hyponymy relations between terms extracted from texts,this model calculates the asymmetry of prerequisite relation among related terms of learning objects,and then predicts the prerequisite relation betweens learning objects.The experimental results show that the proposed method achieves the state-of-the-art performance.

Key words: prerequisite relation, asymmetry, end-to-end model

中图分类号: 

No Suggested Reading articles found!