What is wrong with deep knowledge tracing? Attention-based knowledge tracing

被引:9
作者
Wang, Xianqing [1 ]
Zheng, Zetao [2 ]
Zhu, Jia [3 ]
Yu, Weihao [4 ]
机构
[1] Guangdong Polytech Sci & Technol, Guangzhou, Peoples R China
[2] Univ Elect Sci & Technol China, Chengdu, Peoples R China
[3] Zhejiang Normal Univ, Jinhua, Zhejiang, Peoples R China
[4] Res Inst China Telecom Corp Ltd, Guangzhou, Peoples R China
基金
中国国家自然科学基金;
关键词
Knowledge tracing; Self-attention; Interpretable analysis;
D O I
10.1007/s10489-022-03621-1
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Scientifically and effectively tracking student knowledge states is a significant and fundamental task in personalized education. Many neural network-based models, e.g., deep knowledge tracing (DKT), have achieved remarkable results on knowledge tracing. DKT does not require handcrafted knowledge and can capture more complex representations of student knowledge. However, a severe problem of DKT is that the output fluctuates wildly. In this paper, we utilize a finite state automaton (FSA), a mathematical computation model, to interpret the waviness of DKT because an FSA has observable state evolution in response to external input. With the support of an FSA, we discover that DKT cannot handle long sequential inputs, which leads to unstable predictions. Accordingly, we introduce two novel attention-based models that solve the above problems by directly capturing the relationships among each item of the input sequence. Extensive experimentation on five well-known datasets shows that our two proposed models achieve state-of-the-art performance compared to existing knowledge tracing approaches.
引用
收藏
页码:2850 / 2861
页数:12
相关论文
共 37 条
[1]  
Arthur D., 2007, PROC SODA
[2]  
Bahdanau D., 2015, 3 INT C LEARN REP IC
[3]  
Berant J, 2013, P 2013 C EMP METH NA
[4]  
Cen H, 2006
[5]  
Cheng J, 2016, P 2016 C EMP METH NA
[6]  
Choi Y, 2020, LS20 7 ACM C LEARN S
[7]  
Corbett A T., 1995, USER MODEL USER ADAP
[8]  
Devlin J, 2019, 2019 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL HLT 2019), VOL. 1, P4171
[9]  
Dong X, 2014, 20 ACM SIGKDD INT C
[10]  
Glorot X., 2010, International conference on artificial intelligence and statistics, P249