S-KMN: Integrating semantic features learning and knowledge mapping network for automatic quiz question annotation
Quiz question annotation aims to assign the most relevant knowledge point to a question, which is a key technology to support intelligent education applications. However, the existing methods only extract the explicit semantic information that reveals the literal meaning of a question, and ignore th...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-07-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157823001489 |
| _version_ | 1797749184355368960 |
|---|---|
| author | Jing Wang Hao Li Xu Du Jui-Long Hung Shuoqiu Yang |
| author_facet | Jing Wang Hao Li Xu Du Jui-Long Hung Shuoqiu Yang |
| author_sort | Jing Wang |
| collection | DOAJ |
| description | Quiz question annotation aims to assign the most relevant knowledge point to a question, which is a key technology to support intelligent education applications. However, the existing methods only extract the explicit semantic information that reveals the literal meaning of a question, and ignore the implicit knowledge information that highlights the knowledge intention. To this end, an innovative dual-channel model, the Semantic-Knowledge Mapping Network (S-KMN) is proposed to enrich the question representation from two perspectives, semantic and knowledge, simultaneously. It integrates semantic features learning and knowledge mapping network (KMN) to extract explicit semantic features and implicit knowledge features of questions,respectively. Designing KMN to extract implicit knowledge features is the focus of this study. First, the context-aware and sequence information of knowledge attribute words in the question text is integrated into the knowledge attribute graph to form the knowledge representation of each question. Second, learning a projection matrix, which maps the knowledge representation to the latent knowledge space based on the scene base vectors, and the weighted summations of these base vectors serve as knowledge features. To enrich the question representation, an attention mechanism is introduced to fuse explicit semantic features and implicit knowledge features, which realizes further cognitive processing on the basis of understanding semantics. The experimental results on 19,410 real-world physics quiz questions in 30 knowledge points demonstrate that the S-KMN outperforms the state-of-the-art text classification-based question annotation method. Comprehensive analysis and ablation studies validate the superiority of our model in selecting knowledge-specific features. |
| first_indexed | 2024-03-12T16:15:38Z |
| format | Article |
| id | doaj.art-8c430d4046a748e2965dd25a9ee3d66f |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2024-03-12T16:15:38Z |
| publishDate | 2023-07-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-8c430d4046a748e2965dd25a9ee3d66f2023-08-09T04:32:00ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782023-07-01357101594S-KMN: Integrating semantic features learning and knowledge mapping network for automatic quiz question annotationJing Wang0Hao Li1Xu Du2Jui-Long Hung3Shuoqiu Yang4National Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, ChinaNational Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, China; Corresponding author.National Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, ChinaNational Engineering Laboratory For Educationgal Big Data, Central China Normal University, Wuhan 430079, China; Department of Educational Technology, Boise State University, Boise, ID 83725, USANational Engineering Research Center for E-Learning, Central China Normal University, Wuhan 430079, ChinaQuiz question annotation aims to assign the most relevant knowledge point to a question, which is a key technology to support intelligent education applications. However, the existing methods only extract the explicit semantic information that reveals the literal meaning of a question, and ignore the implicit knowledge information that highlights the knowledge intention. To this end, an innovative dual-channel model, the Semantic-Knowledge Mapping Network (S-KMN) is proposed to enrich the question representation from two perspectives, semantic and knowledge, simultaneously. It integrates semantic features learning and knowledge mapping network (KMN) to extract explicit semantic features and implicit knowledge features of questions,respectively. Designing KMN to extract implicit knowledge features is the focus of this study. First, the context-aware and sequence information of knowledge attribute words in the question text is integrated into the knowledge attribute graph to form the knowledge representation of each question. Second, learning a projection matrix, which maps the knowledge representation to the latent knowledge space based on the scene base vectors, and the weighted summations of these base vectors serve as knowledge features. To enrich the question representation, an attention mechanism is introduced to fuse explicit semantic features and implicit knowledge features, which realizes further cognitive processing on the basis of understanding semantics. The experimental results on 19,410 real-world physics quiz questions in 30 knowledge points demonstrate that the S-KMN outperforms the state-of-the-art text classification-based question annotation method. Comprehensive analysis and ablation studies validate the superiority of our model in selecting knowledge-specific features.http://www.sciencedirect.com/science/article/pii/S1319157823001489Automatic quiz question annotationKnowledge mapping networkKnowledge attribute graphLatent knowledge spaceSemantic-knowledge features |
| spellingShingle | Jing Wang Hao Li Xu Du Jui-Long Hung Shuoqiu Yang S-KMN: Integrating semantic features learning and knowledge mapping network for automatic quiz question annotation Journal of King Saud University: Computer and Information Sciences Automatic quiz question annotation Knowledge mapping network Knowledge attribute graph Latent knowledge space Semantic-knowledge features |
| title | S-KMN: Integrating semantic features learning and knowledge mapping network for automatic quiz question annotation |
| title_full | S-KMN: Integrating semantic features learning and knowledge mapping network for automatic quiz question annotation |
| title_fullStr | S-KMN: Integrating semantic features learning and knowledge mapping network for automatic quiz question annotation |
| title_full_unstemmed | S-KMN: Integrating semantic features learning and knowledge mapping network for automatic quiz question annotation |
| title_short | S-KMN: Integrating semantic features learning and knowledge mapping network for automatic quiz question annotation |
| title_sort | s kmn integrating semantic features learning and knowledge mapping network for automatic quiz question annotation |
| topic | Automatic quiz question annotation Knowledge mapping network Knowledge attribute graph Latent knowledge space Semantic-knowledge features |
| url | http://www.sciencedirect.com/science/article/pii/S1319157823001489 |
| work_keys_str_mv | AT jingwang skmnintegratingsemanticfeatureslearningandknowledgemappingnetworkforautomaticquizquestionannotation AT haoli skmnintegratingsemanticfeatureslearningandknowledgemappingnetworkforautomaticquizquestionannotation AT xudu skmnintegratingsemanticfeatureslearningandknowledgemappingnetworkforautomaticquizquestionannotation AT juilonghung skmnintegratingsemanticfeatureslearningandknowledgemappingnetworkforautomaticquizquestionannotation AT shuoqiuyang skmnintegratingsemanticfeatureslearningandknowledgemappingnetworkforautomaticquizquestionannotation |