Development of Knowledge Graph Construction and Intelligent Question Answering System in Education Based on Transformer Model
Main Article Content
Abstract
Efficient semantic information processing and multi-hop knowledge reasoning have become essential technologies for intelligent information services and next-generation networked systems. To address inaccurate semantic understanding caused by short or ambiguous queries and insufficient reasoning capability under fragmented knowledge structures, this study proposes an intelligent question answering framework that tightly integrates Transformer-based semantic encoding with graph attention reasoning. The proposed architecture employs DeBERTa-v3-base and conditional random fields for entity recognition, combines dual-tower vector retrieval with cross-encoder reranking for semantic disambiguation, and constructs k-hop knowledge subgraphs enhanced by multi-layer Graph Attention Networks to achieve relation-aware information propagation and evidence aggregation. A multi-task joint optimization strategy incorporating adaptive gradient normalization, adjacency reconstruction regularization, and negative sampling is further introduced to improve long-tail generalization and reasoning robustness. Neo4j graph storage and FAISS vector indexing enable near real-time retrieval and scalable deployment. Experimental evaluation demonstrates high semantic understanding accuracy, interpretable multi-hop reasoning capability, and stable performance under short and colloquial queries, with superior Exact Match and path reasoning accuracy compared with baseline models. Beyond educational applications, the proposed framework provides an effective methodology for semantic information fusion, distributed knowledge reasoning, intelligent query processing, and adaptive decision support, offering valuable references for communication-enabled information systems, networked knowledge services, and intelligent information infrastructures related to Electromagnetic Waves, Antennas and Propagation engineering applications.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
C. Yi, R. Zhu, and Q. Wang, “Exploring the interplay between question-answering systems and communication with instructors in facilitating learning,” Internet Research, vol. 32, no. 7, pp. 32-55, 2022, doi: 10.1108/INTR-08-2020-0459.
G. Lee and X. Zhai, “Realizing visual question answering for education: GPT-4V as a multimodal AI,” TechTrends, vol. 69, no. 2, pp. 271-287, 2025, doi: 10.1007/s11528-024-01035-z.
E. Bernasconi, D. Redavid, and S. Ferilli, “Enhancing Personalized Learning with a Context-Aware Intelligent Question-Answering System and Automated Frequently Asked Question Generation,” Electronics, vol. 14, no. 7, pp. 1481-1506, 2025, doi: 10.3390/electronics14071481.
Y. Cheng, “Application of a neural network-based visual question answering system in preschool language education,” IEIE Transactions on Smart Processing & Computing, vol. 12, no. 5, pp. 419-427, 2023, doi: 10.5573/IEIESPC.2023.12.5.419.
S. Ehsani and J. Liu, “Elevating Textual Question Answering with On-Demand Visual Augmentation,” ACM Transactions on Multimedia Computing, Communications and Applications, vol. 21, no. 10, pp. 1-25, 2025, doi: 10.1145/3729231.
H. A. Alawwad, A. Alhothali, U. Naseem, A. Alkhathlan, and A. Jamal, “Enhancing textual textbook question answering with large language models and retrieval augmented generation,” Pattern Recognition, vol. 162, no. 1, pp. 1-11, 2025, doi: 10.1016/j.patcog.2024.111332.
Q. Zhong, Y. Jiang, and H. Du, “Intelligent Q&A system for distance education in universities based on Chinese word segmentation technology,” International Journal of Continuing Engineering Education and Life Long Learning, vol. 34, no. 6, pp. 562-576, 2024, doi: 10.1504/IJCEELL.2024.143312.
T. T. Aurpa, R. K. Rifat, M. S. Ahmed, M. M. Anwar, and A. B. M. S. Ali, “Reading comprehension based question answering system in Bangla language with transformer-based learning,” Heliyon, vol. 8, no. 10, pp. 1-11, 2022, doi: 10.1016/j.heliyon.2022.e11052.
K. Nassiri and M. Akhloufi, “Transformer models used for text-based question answering systems,” Applied Intelligence, vol. 53, no. 9, pp. 10602-10635, 2023, doi: 10.1007/s10489-022-04052-8.
F. Dartiko, M. Yusa, A. Erlansari, and S. A. Basha, “Comparative analysis of transformer-based method in a question answering system for campus orientation guides,” INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi, vol. 8, no. 1, pp. 126-143, 2024, doi: 10.29407/intensif.v8i1.21971.
Y. Ba, “Advancing Educational Management with the ATT-MR-WL Intelligent Question-Answering Model,” Journal of Web Engineering, vol. 23, no. 7, pp. 973-1002, 2024, doi: 10.13052/jwe1540-9589.2373.
Y. Zhu, “A knowledge graph and BiLSTM-CRF-enabled intelligent adaptive learning model and its potential application,” Alexandria Engineering Journal, vol. 91, no. 1, pp. 305-320, 2024, doi: 10.1016/j.aej.2024.02.011.
H. Yu, E. Wang, Q. Lang, and J. Wang, “Intelligent retrieval and comprehension of entrepreneurship education resources based on semantic summarization of knowledge graphs,” IEEE Transactions on Learning Technologies, vol. 17, no. 1, pp. 1198-1209, 2024, doi: 10.1109/TLT.2024.3364155.
J. Xiao and Z. Zhang, “EduVQA: A multimodal Visual Question Answering framework for smart education,” Alexandria Engineering Journal, vol. 122, no. 1, pp. 615-624, 2025, doi: 10.1016/j.aej.2025.03.005.
X. Cao and Y. Liu, “Relmkg: reasoning with pre-trained language models and knowledge graphs for complex question answering,” Applied Intelligence, vol. 53, no. 10, pp. 12032-12046, 2023, doi: 10.1007/s10489-022-04123-w.
W. Lu, D. Ming, X. Mao, J. Wang, Z. Zhao, and Y. Cheng, “A DeBERTa-Based Semantic Conversion Model for Spatiotemporal Questions in Natural Language,” Applied Sciences, vol. 15, no. 3, pp. 1073-1093, 2025, doi: 10.3390/app15031073.
S. Li, J. Cao, J. Yang, Y. He, and P. Wang, “DPRM: DeBERTa-based potential relationship multi-headed self-attention joint extraction model,” PLoS One, vol. 20, no. 8, pp. 1-26, 2025, doi: 10.1371/journal.pone.0329120.
G. Zhang, J. Liu, G. Zhou, K. Zhao, Z. Xie, and B. Huang, “Question-directed reasoning with relation-aware graph attention network for complex question answering over knowledge graph,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32, no. 1, pp. 1915-1927, 2024, doi: 10.1109/TASLP.2024.3375631.
P. He and J. Chen, “Enhancing question answering in educational knowledge bases using question-aware graph convolutional network,” Journal of Intelligent & Fuzzy Systems, vol. 45, no. 6, pp. 12037-12048, 2023, doi: 10.3233/JIFS-233915.
Y. Fang, J. Deng, F. Zhang, and H. Wang, “An intelligent question-answering model over educational knowledge graph for sustainable urban living,” Sustainability, vol. 15, no. 2, pp. 1139-1157, 2023, doi: 10.3390/su15021139.
Y. Jeong and E. Kim, “Scideberta: Learning deberta for science technology documents and fine-tuning information extraction tasks,” IEEE Access, vol. 10, no. 1, pp. 60805-60813, 2022, doi: 10.1109/ACCESS.2022.3180830.
D. Han, Z. Wang, Y. Li, X. Ma, and J. Zhang, “Segmentation-aware relational graph convolutional network with multi-layer CRF for nested named entity recognition,” Complex & Intelligent Systems, vol. 10, no. 6, pp. 7893-7905, 2024, doi: 10.1007/s40747-024-01551-8.
Y. Qiu, L. Dong, W. Zhang, H. Xing, and J. Huang, “A diffusion enhanced CRF and BiLSTM framework for accurate entity recognition,” Scientific Reports, vol. 15, no. 1, pp. 1-25, 2025, doi: 10.1038/s41598-025-04036-x.
W. Khan, A. Daud, K. Shahzad, T. Amjad, A. Banjar, and H. Fasihuddin, “Named entity recognition using conditional random fields,” Applied Sciences, vol. 12, no. 13, pp. 6391-6408, 2022, doi: 10.1016/j.procs.2020.03.431.
Q. Z. Lim, C. P. Lee, K. M. Lim, J. X. Ng, E. K. H. Ooi, and N. K. N. Loh, “Multilingual question answering for Malaysia history with transformer-based language model,” Emerging Science Journal, vol. 8, no. 2, pp. 675-686, 2024, doi: 10.28991/ESJ-2024-08-02-019.
J. Zhu, “A multi task learning framework using DeBERTa and BWO optimization for enhancing long term english vocabulary memory,” Discover Computing, vol. 28, no. 1, pp. 1-32, 2025, doi: 10.1007/s10791-025-09690-3.
Y. Miao, W. Cheng, S. He, and H. Jiang, “Research on visual question answering based on GAT relational reasoning,” Neural Processing Letters, vol. 54, no. 2, pp. 1435-1448, 2022, doi: 10.1007/s11063-021-10689-2.
Z. Li, Z. Cao, P. Li, Y. Zhong, and S. Li, “Multi-hop question generation with knowledge graph-enhanced language model,” Applied Sciences, vol. 13, no. 9, pp. 5765-5779, 2023, doi: 10.3390/app13095765.
Y. Li, W. Li, and L. Nie, “Dynamic graph reasoning for conversational open-domain question answering,” ACM Transactions on Information Systems (TOIS), vol. 40, no. 4, pp. 1-24, 2022, doi: 10.1145/3498557.
P. Zhu, Y. Yuan, and L. Chen, “Electra-based graph network model for multi-hop question answering,” Journal of Intelligent Information Systems, vol. 61, no. 3, pp. 819-834, 2023, doi: 10.1007/s10844-023-00800-5.
A. A. Yusuf, C. Feng, X. Mao, R. Ally Duma, M. S. Abood, and A. H. A. Chukkol, “Graph neural networks for visual question answering: a systematic review,” Multimedia Tools and Applications, vol. 83, no. 18, pp. 55471-55508, 2024, doi: 10.1007/s11042-023-17594-x.
M. Reyad, A. M. Sarhan, and M. Arafa, “A modified Adam algorithm for deep neural network optimization,” Neural Computing and Applications, vol. 35, no. 23, pp. 17095-17112, 2023, doi: 10.1007/s00521-023-08568-z.
P. Zhou, X. Xie, Z. Lin, and S. Yan, “Towards understanding convergence and generalization of AdamW,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 46, no. 9, pp. 6486-6493, 2024, doi: 10.1109/TPAMI.2024.3382294.
I. V. Modoranu, M. Safaryan, G. Malinovsky, E. Kurtic, T. Robert, P. Richtarik, et al., “Microadam: Accurate adaptive optimization with low space overhead and provable convergence,” Advances in Neural Information Processing Systems, vol. 37, no. 1, pp. 1-43, 2024, doi: 10.52202/079017-0001.
C. Zhang, Y. Shao, H. Sun, L. Xing, Q. Zhao, and L. Zhang, “The WuC-Adam algorithm based on joint improvement of Warmup and cosine annealing algorithms,” Mathematical Biosciences and Engineering, vol. 21, no. 1, pp. 1270-1285, 2024, doi: 10.3934/mbe.2024054.
O. V. Johnson, C. Xinying, K. W. Khaw, and M. H. Lee, “ps-CALR: periodic-shift cosine annealing learning rate for deep neural networks,” IEEE Access, vol. 11, no. 1, pp. 139171-139186, 2023, doi: 10.1109/ACCESS.2023.3340719.