知识主题间先序关系挖掘

doi:10.11959/j.issn.2096-0271.2020052

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

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 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 MA^1,²,Bifan WEI^1,²,Jie MA^1,²,Jun LIU^1,²,Yi HUANG³,Min HU³,Junlan FENG³

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/Abstract

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:

TP391.1

麻珂欣, 魏笔凡, 马杰, 刘均, 黄毅, 胡珉, 冯俊兰. 知识主题间先序关系挖掘[J]. 大数据, 2020, 6(6): 26-39.

Kexin MA, Bifan WEI, Jie MA, Jun LIU, Yi HUANG, Min HU, Junlan FENG. Mining prerequisite relations among learning objects[J]. Big Data Research, 2020, 6(6): 26-39.

图/表 7

图1

图2

图3

图4?

表1

表2

图5

参考文献 29

[1]	LIANG C , WU Z , HUANG W ,et al. Measuring prerequisite relations among concepts[C]// 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg:ACL Press, 2015: 1668-1674.
[2]	WILEY D A . Learning object design and sequencing theory[D]. Provo:Brigham Young University, 2000.
[3]	ZHU H , TIAN F , WU K ,et al. A multiconstraint learning path recommendation algorithm based on knowledge map[J]. Knowledge-Based Systems, 2018,143: 102-114.
[4]	AGRAWAL R , GOLSHAN B , PAPALEXAKIS E . Toward data-driven design of educational courses:a feasibility study[J]. Journal of Educational Data Mining, 2016,8(1): 1-21.
[5]	CHEN P , LU Y , ZHENG V W ,et al. Prerequisite-driven deep knowledge tracing[C]// 2018 IEEE International Conference on Data Mining (ICDM). Piscataway:IEEE Press, 2018: 39-48.
[6]	LYU P , WANG X , XU J ,et al. Utilizing knowledge graph and student testing behavior data for personalized exercise recommendation[C]// ACM Turing Celebration Conference-China. New York:ACM Press, 2018: 53-59.
[7]	CHEN W , LAN A S , CAO D ,et al. Behavioral analysis at scale:learning course prerequisite structures from learner click streams[C]// The 11th International Conference on Educational Data Mining.[S.l.:s.n. ], 2018: 66-75.
[8]	ALSAAN F , BOUGHOULA A , GEIGLE C ,et al. Mining MOOC lecture transcripts to construct concept dependency graphs[C]// The 11th International Conference on Educational Data Mining.[S.l.:s.n. ], 2018: 467-473.
[9]	CHAPLOT D S , YANG Y , CARBONELL J ,et al. Data-driven automated induction of prerequisite structure graphs[C]// The 9th International Conference on Educational Data Mining.[S.l.:s.n. ], 2016: 318-321.
[10]	PIECH C , BASSEN J , HUANG J ,et al. Deep knowledge tracing[C]// Advances in Neural Information Processing Systems. Cambridge:MIT Press, 2015: 505-513.
[11]	DE MEDIO C , GASPARETTI F , LIMONGELLI C ,et al. Automatic extraction and sequencing of Wikipedia pages for smart course building[C]// 2017 21st International Conference Information Visualisation (IV). Piscataway:IEEE Press, 2017: 378-383.
[12]	LIANG C , YE J , WANG S ,et al. Investigating active learning for concept prerequisite learning[C]// The 32nd AAAI Conference on Artificial Intelligence. Menlo Park:AAAI Press, 2018: 7913-7919.
[13]	TALUKDAR P , COHEN W . Crowdsourced comprehension:predicting prerequisite structure in Wikipedia[C]// The 7th Workshop on Building Educational Applications Using NLP. Stroudsburg:ACL Press, 2012: 307-315.
[14]	UPADHYAY P , BINDAL A , KUMAR M ,et al. Construction and applications of TeKnowbase:a knowledge base of computer science concepts[C]// The Web Conference 2018. Canton of Geneva:International World Wide Web Conferences Steering Committee, 2018: 1023-1030.
[15]	WANG S , ORORBIA A , WU Z ,et al. Using prerequisites to extract concept maps from textbooks[C]// The 25th ACM International Conference on Information and Knowledge Management. New York:ACM Press, 2016: 317-326.
[16]	GASPARETTI F , DE MEDIO C , LIMONGELLI C ,et al. Prerequisites between learning objects:automatic extraction based on a machine learning approach[J]. Telematics and Informatics, 2018,35(3): 595-610.
[17]	MANRIQUE R , . Towards automatic learning content sequence via linked open data[C]// The International Conference on Web Intelligence. New York:ACM Press, 2017: 1230-1233.
[18]	LEE K , HE L , LEWIS M ,et al. End-toend neural coreference resolution[C]// The 2017 Conference on Empirical Methods in Natural Language Processing. Stroudsburg:ACL Press, 2017: 188-197.
[19]	MA J , LIU J , LI Y ,et al. Jointly optimized neural coreference resolution with mutual attention[C]// The 13th International Conference on Web Search and Data Mining. New York:ACM Press, 2020: 402-410.
[20]	VUONG A , NIXON T , TOWLE B . A method for finding prerequisites within a curriculum[C]// The 4th International Conference on Educational Data Mining.[S.l.:s.n]. 2011: 211-216.
[21]	LIANG C , YE J , WU Z ,et al. Recovering concept prerequisite relations from university course dependencies[C]// The 31st AAAI Conference on Artificial Intelligence. Menlo Park:AAAI Press, 2017: 4786-4791.
[22]	ROY S , MADHYASTHA M , LAWRENCE S ,et al. Inferring concept prerequisite relations from online educational resources[C]// The 33rd AAAI Conference on Artificial Intelligence. Menlo Park:AAAI Press, 2019: 9589-9594.
[23]	LIU J , JIANG L , WU Z ,et al. Mining learning-dependency between knowledge units from text[J]. The VLDB Journal, 2011,20(3): 335-345.
[24]	ADORNI G , DELL’ORLETTA F , KOCEVA F ,et al. Extracting dependency relations from digital learning content[C]// Italian Research Conference on Digital Libraries. Heidelberg:Springer, 2018: 114-119.
[25]	NAFA F , KHAN J I , OTHMAN S ,et al. Mining cognitive skills levels of knowledge units in text using graph tringluarity mining[C]// 2016 IEEE/WIC/ACM International Conference on Web Intelligence Workshops (WIW). Piscataway:IEEE Press, 2016: 1-4.
[26]	MIASCHI A , ALZETTA C , CARDILLO F A ,et al. Linguistically-driven strategy for concept prerequisites learning on Italian[C]// The 14th Workshop on Innovative Use of NLP for Building Educational Applications. Stroudsburg:ACL Press, 2019: 285-295.
[27]	FILLMORE C J . Frame semantics[J]. Cognitive Linguistics:Basic Readings, 2006,34: 373-400.
[28]	LEE K , HE L , ZETTLEMOYER L . Higher-order coreference resolution with coarse-to-fine inference[C]// The 2018 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies,Volume 2 (Short Papers). Stroudsburg:ACL Press, 2018: 687-692.
[29]	HOCHREITER S , SCHMIDHUBER J . Long short-term memory[J]. Neural Computation, 1997,9(8): 1735-1780.

领域	MaxEnt	RefD	MLP	端到端模型
领域	MaxEnt	RefD	MLP	相同权重策略	不同权重策略
减数分裂	51.0%	55.7%	79.0%	65.7%	77.12%
公钥加密	67.1%	57.7%	58.0%	72.4%	85.93%
平行假设	64.7%	67.9%	85.0%	51.7%	80.79%
牛顿定律	53.9%	64.6%	68.0%	45.5%	86.99%
全球变暖	56.8%	60.1%	82.0%	33.5%	84.26%
平均	58.7%	61.2%	74.4%	53.8%	83.02%

知识主题间先序关系挖掘

Mining prerequisite relations among learning objects

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 29

相关文章 14

Metrics

推荐阅读 0

领域	知识主题对数量/个	先序关系对数量/个
减数分裂	400	67
公钥加密	200	27
平行假设	200	25
牛顿定律	400	44
全球变暖	400	43

[1]	于亚秀, 李欣. 数字人文视域中的古籍文本标注方法研究——以MARKUS为例[J]. 大数据, 2022, 8(6): 15-25.
[2]	崔雨萌, 王靖亚, 闫尚义, 陶知众. 基于深度学习的警情记录关键信息自动抽取[J]. 大数据, 2022, 8(6): 127-142.
[3]	韩立帆, 季紫荆, 陈子睿, 王鑫. 数字人文视域下面向历史古籍的信息抽取方法研究[J]. 大数据, 2022, 8(6): 26-39.
[4]	关海山, 郑玉龙, 魏笔凡, 张泽民, 岳浩, 师斌, 董博. 税收优惠政策关键要素抽取与可视化分析[J]. 大数据, 2022, 8(5): 106-123.
[5]	徐康庭, 宋威. 结合语言知识和深度学习的中文文本情感分析方法[J]. 大数据, 2022, 8(3): 115-127.
[6]	肖晓霞, 刘明婷, 杨冯天赐, 刘鉴建县, 杨阳, 石月. 基于NLP的中医医案文本快速结构化方法[J]. 大数据, 2022, 8(3): 128-139.
[7]	黄辉, 秦永彬, 陈艳平, 黄瑞章. 基于BERT阅读理解框架的司法要素抽取方法[J]. 大数据, 2021, 7(6): 19-29.
[8]	孙倩, 秦永彬, 黄瑞章, 刘丽娟, 陈艳平. 结合案件要素序列的罪名预测方法[J]. 大数据, 2021, 7(6): 30-40.
[9]	王文广. 知识图谱推理：现代的方法与应用[J]. 大数据, 2021, 7(3): 42-59.
[10]	肖时耀, 吕慰, 陈洒然, 秦烁, 黄格, 蔡梦思, 谭跃进, 谭旭, 吕欣. 基于百度贴吧的HIV高危人群特征分析[J]. 大数据, 2019, 5(1): 98-108.
[11]	杜小勇, 陈跃国. 大数据的价值发现方法[J]. 大数据, 2017, 3(2): 19-25.
[12]	赵妍妍,秦兵,刘挺. 社会焦点透视镜系统—— 大数据视角下的舆情观测平台[J]. 大数据, 2016, 2(2): 46-55.
[13]	程学旗, 兰艳艳. 网络大数据的文本内容分析[J]. 大数据, 2015, 1(3): 62-71.
[14]	袁书寒, 向阳, 鄂世嘉. 基于特征学习的文本大数据内容理解及其发展趋势[J]. 大数据, 2015, 1(3): 72-81.