计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (10): 162-169.doi: 10.11896/jsjkx.240400090

• 智能教育技术及应用 • 上一篇    下一篇

先决条件关系信息增强的课程知识图谱关系预测方法

杨佳琦1, 贺超波1, 官全龙2, 林晓凡3, 梁卓明4, 罗辉琼4   

  1. 1 华南师范大学计算机学院 广州 510631
    2 暨南大学信息科学技术学院 广州 510632
    3 华南师范大学教育信息技术学院 广州 510631
    4 华南师范大学网络信息中心 广州 510631
  • 收稿日期:2024-04-15 修回日期:2024-07-01 出版日期:2024-10-15 发布日期:2024-10-11
  • 通讯作者: 贺超波(hechaobo@foxmail.com)
  • 作者简介:(2022023277@m.scnu.edu.cn)
  • 基金资助:
    国家自然科学基金(62077045);广东省基础与应用基础研究基金(2024A1515011758)

Prerequisite Relation Information Enhanced Relation Prediction Method for Course KnowledgeGraph

YANG Jiaqi1, HE Chaobo1, GUAN Quanlong2, LIN Xiaofan3, LIANG Zhuoming4, LUO Huiqiong4   

  1. 1 School of Computer Science,South China Normal University,Guangzhou 510631,China
    2 School of Information Science and Technology,Jinan University,Guangzhou 510632,China
    3 School of Educational Information Technology,South China Normal University,Guangzhou 510631,China
    4 Network Information Center,South China Normal University,Guangzhou 510631,China
  • Received:2024-04-15 Revised:2024-07-01 Online:2024-10-15 Published:2024-10-11
  • About author:YANG Jiaqi,born in 2000,postgra-duate,is a member of CCF(No.R5525G).Her main research interests include knowledge graph and graph neural networks.
    HE Chaobo,born in 1981,professor,Ph.D supervisor,is a senior member of CCF(No.13911S).His main research interests include graph data mining and intelligent education.
  • Supported by:
    National Natural Science Foundation of China(62077045) and Guangdong Basic and Applied Basic Research Foundation(2024A1515011758).

PDF (PC)

261

摘要： 大量课程知识图谱在自动答疑、学习路径规划及学习资源推荐等智能化教学应用中发挥着重要的支撑作用,然而实体间关系缺失导致的不完整问题显著降低了它们的应用价值。关系预测是自动化补全课程知识图谱缺失关系的主要手段,但现有方法仅直接使用稀疏的拓扑结构信息,未能挖掘利用其特有的先决条件关系信息进一步提升预测性能。针对该问题,设计了一种先决条件关系信息增强的课程知识图谱关系预测方法PRIERP。该方法首先设计基于语义路径计算的先决条件关系信息提取机制,然后分别基于拓扑结构信息和先决条件关系信息构建双视图,并设计有向图Transformer从双视图学习课程知识图谱的低维表征,最后基于多层感知机分类模型实现端到端的关系预测。在两个典型课程知识图谱HhsMath和ML上进行相关实验,结果表明PRIERP优于其他代表性方法。在HhsMath中,PRIERP在MRR,Hits@1,Hits@3和Hits@10评价指标上相比基线方法至少分别提升2.43%,5.93%,4.73%和1.72%。此外,关系预测的典型案例分析结果也证明了PRIERP的有效性。

关键词: 课程知识图谱, 关系预测, 先决条件关系, 图Transformer

Abstract: A large amount of course knowledge graphs have played a crucial role in intelligent teaching applications such as automatic Q&A,learning path planning,and learning resource recommendation.However,the incompleteness issue caused by missing entity relations significantly reduces their application value.Relation prediction is the primary means of automatically completing the missing relations in course knowledge graphs,but existing methods only directly use sparse topology information and fail to exploit and enhance the prediction performance by further using its unique prerequisite relation information.To address this pro-blem,a course knowledge graph relation prediction method,prerequisite relation information enhanced relation prediction(PRIERP),is proposed.This method first designs a prerequisite relation information extraction mechanism based on semantic path computation.Then,it constructs dual views based on topology information and prerequisite relation information,and designs a directed graph Transformer to learn the low-dimentional representation of the course knowledge graph from the dual views.Finally,an end-to-end relation prediction is achieved based on a multi-layer perceptron classification model.Experiments are conducted on two typical course knowledge graphs HhsMath and ML.The results demonstrate that PRIERP outperforms other representative methods.In HhsMath,PRIERP achieves at least 2.43%,5.93%,4.73% and 1.72% improvements in terms of MRR,Hits@1,Hits@3,and Hits@10 metrics,respectively.Furthermore,the analysis of typical cases in relation prediction also confirms its effectiveness.

Key words: Course knowledge graph, Relation prediction, Prerequisite relation, Graph transformer

中图分类号: 

  • TP391
[1]ZHOU D D,DONG X X,GU H N.New Trends in Research on Knowledge Graphs in the Field of Education:Subject Teaching Graphs[J].Research in Educational Technology,2024,45(2):91-97,120.
[2]BAI J,LIU X,WANG W,et al.Complex Query Answering onEventuality Knowledge Graph with Implicit Logical Constraints[C]//Thirty-seventh Conference on Neural Information Processing Systems.2024:1-20.
[3]CUI C,YAO Y,ZHANG C,et al.DGEKT:a dual graph ensem-ble learning method for knowledge tracing[J].ACM Transactions on Information Systems,2024,42(3):1-24.
[4]AIN Q U,CHATTI M A,METENG KAMDEM P A,et al.Learner Modeling and Recommendation of Learning Resources using Personal Knowledge Graphs[C]//Proceedings of the 14th Learning Analytics and Knowledge Conference.2024:273-283.
[5]ZHANG X M,LIU S,WANG H Y,et al.Personalized learningpath recommendation for e-learning based on knowledge graph and graph convolutional network[J].International Journal of Software Engineering and Knowledge Engineering,2023,33(1):109-131.
[6]BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[C]//Advances in Neural Information Processing Systems.2013:2787-2795.
[7]YANG B,YIH S,HE X D,et al.Embedding Entities and Relations for Learning and Inference in Knowledge Bases[C]//Proceedings of the International Conference on Learning Representations.2015:1-12.
[8]WANG Z,ZHANG J,FENG J,et al.Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence.2014:1112-1119.
[9]SUN Z,DENG Z H,NIE J Y,et al.RotatE:Knowledge Graph Embedding by Relational Rotation in Complex Space[C]//International Conference on Learning Representations.2018:809-816.
[10]NICKEL M,TRESP V,KRIEGEL H P.A three-way model forcollective learning on multi-relational data[C]//Proceedings of the 28th International Conference on International Conference on Machine Learning.2011:809-816.
[11]SCHLICHTKRULL M,KIPF T N,BLOEM P,et al.Modeling relational data with graph convolutional networks[C]//The Semantic Web:15th International Conference.2018:593-607.
[12]VASHISHTH S,SOUMYA S,VIKRAM N,et al.Composition-based Multi-Relational Graph Convolutional Networks[C]//International Conference on Learning Representations.2019:1-16.
[13]清华大学知识工程研究室.MoocData[EB/OL].[2024-05-16].http://moocdata.cn/data/prerequisite-relation.
[14]YU J,LUO G,XIAO T,et al.MOOCCube:a large-scale data repository for NLP applications in MOOCs [C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:3135-3142.
[15]LI I,FABBRI A R,TUNG R R,et al.What should I learn first:introducing lecturebank for NLP education and prerequisite chain learning [C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:6674-6681.
[16]SUN F P,YU M,TANG J S,et al.Research on the recommendation of Chinese vocabulary learning resources based on know-ledge graph-taking HSK Level 3 vocabulary as an example [J].Modern Educational Technology,2021,31(1):76-82.
[17]XIE J,YANG H Y,LIANG F M,et al.Design and development of intelligent question answering system based on course graph－taking signal and system as an example [J/OL].Journal of systems science.(2023-07-18)[2024-03-30].http://kns.cnki.net/kcms/detail/14.1333.N.20230717.1421.002.html.
[18]CHEN Z Y,SHANG Y,QIAN D M.Research on intelligentquestion answering system based on knowledge graph [J].Computer Applications and Software,2018,35(2):178-182.
[19]ZHANG C X,PENG C,LUO M Q,et al.Construction and reasoning of mathematics course knowledge graph [J].Computer Science,2020,47(S2):573-578.
[20]MU S,TAN Z Q,LUO J X,et al.Research on the construction method of three-dimensional knowledge graph for precision teaching and research [J].Audio-visual Education Research,2023,44(5):74-81.
[21]TONG X K,ZHU X J,WANG X H,et al.Multi-objective cross-domain recommendation method for digital cultural resource knowledge graph[J].Journal of Computer Engineering and Applications,2023,59(10):142-150.
[22]LIN J,KE Q C,HUANG Z H,et al.Dynamic generation of subject knowledge graph and its application in intelligent resource organization [J].Journal of Distance Education,2012,40(4):23-34.
[23]DETTMERS T,MINERVINI P,STENETORP P,et al.Convolutional 2D knowledge graph embeddings[C]//32nd AAAI Conference on Artificial Intelligence.2018:1811-1818.
[24]NGUYEN T D,NGUYEN D Q,PHUNG D,et al.A novel embedding model for knowledge base completion based on convolutional neural network[J].arXiv:1712.02121,2017.
[25]JIANG X,WANG Q,WANG B.Adaptive convolution for multi-relational learning[C]//Proceedings of NAACL-HLT.2019:978-987.
[26]YANG Y,ZHANG C,SONG X,et al.Contextualized knowledge graph embedding for explainable talent training course recommendation[J].ACM Transactions on Information Systems,2023,42(2):1-27.
[27]TONG V,NGUYEN D Q,PHUNG D,et al.Two-view graph neural networks for knowledge graph completion[C]//European Semantic Web Conference.Cham:Springer Nature Switzerland.2023:262-278.
[28]BI Z,CHENG S,CHEN J,et al.Relphormer:relational graphtransformer for knowledge graph representations[J].Neurocomputing,2024,566:1-11.
[29]SHANG B,ZHAO Y,LIU J,et al.Mixed geometry message and trainable convolutional attention network for knowledge graph completion[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2024:8966-8974.
[30]TAN Z,CHEN Z,FENG S,et al.KRACL:contrastive learning with graph context modeling for sparse knowledge graph completion[C]//Proceedings of the ACM Web Conference 2023.2023:2548-2559.
[31]LI X,MA J,YU J,et al.A structure-enhanced generative adversarial network for knowledge graph zero-shot relational learning[J].Information Sciences,2023,629:169-183.
[32]HU Y,OUYANG S,YANG Z,et al.Exploring task unification in graph representation learning via generative approach [DB/OL].(2024-03-21)[2024-04-08].https://arxiv.org/abs/2403.14340.
[33]MANRIQUE R,BERNARDO P,OLGA M,et al.Exploringknowledge graphs for the identification of concept prerequisites[J].Smart Learning Environments,2019,6(1):21.
[34]王嘉宁.自然语言处理数据集——高中数学学科[EB/OL].(2019-02-19)[2024-05-16].https://download.csdn.net/download/qq_36426650/10965347.
[35]WANG J.Math-KG:Construction and applications of mathe-matical knowledge graph [DB/OL].(2022-05-08)[2024-03-21].https://arxiv.org/abs/2205.03772.
[36]PAN L,LI C,LI J,et al.Prerequisite relation learning for concepts in moocs [C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.2017:1447-1456.
[37]CAO Y,XU Q,YANG Z,et al.Dual quaternion knowledgegraph embeddings[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:6894-6902.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发