Knowledge Graph (KG) and neural network (NN) based Question-answering (QA) systems have evolved into the realm of intelligent information retrieval as they have been able to reach a high level of precision in terms of capturing user-to-query understanding. However, more traditional systems still face various stumbling blocks, including those with limited data sources, incomplete feature extraction, and low accuracy. This research represents a question-answer system to implement deep learning technology linked with knowledge graphs applied to KGs and neural networks to tackle these inefficiencies. The knowledge base is subjected to the model and it is then used to predict the necessary entities for the user to select the answer from the options displayed. From the experiments, it is clear that the implementation is more reliable and effective than previous processes. The paper introduces a prototype application that can graphically display Q&A results, and this includes a dual-data-source model for upgrading question understanding and increasing accuracy.
Cite this paper
Obono, B. M. and Liu, W. (2025). Knowledge Graph Question-Answering Method Based on Neural Networks. Open Access Library Journal, 12, e3270. doi: http://dx.doi.org/10.4236/oalib.1113270.
Abbas, F., Malik, M.K., Rashid, M.U. and Zafar, R. (2016) WikiQA—A Question Answering System on Wikipedia Using Freebase, Dbpedia and Infobox. 2016 6th International Conference on Innovative Computing Technology (INTECH), Dublin, 24-26 August 2016, 185-193. https://doi.org/10.1109/intech.2016.7845035
Agarwal, R., Liang, C., Schuurmans, D. and Norouzi, M. (2019) Learning to Generalize from Sparse and Underspecified Rewards. International Conference on Machine Learning, Long Beach, 9-15 June 2019, 130-140.
Alvarez-Melis, D. and Jaakkola, T.S. (2017) Tree-Structured Decoding with Doubly-Recurrent Neural Networks. International Conference on Learning Representations, Toulon, 24-26 April 2017, 50-62.
Azmy, M., Shi, P., Lin, J. and Ilyas, I. (2018) Farewell Free-base: Migrating the Simple Questions Dataset to DBpedia. Proceedings of the 27th International Conference on Computational Linguistics, Santa Fe, 20-26 August 2018, 2093-2103.
Bao, J., Duan, N., Yan, Z., Zhou, M. and Zhao, T. (2016) Con-straint-Based Question Answering with Knowledge Graph. Proceedings of COL-ING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, Osaka, 11-16 December 2016, 2503-2514.
Lin, J., Zhao, Y., Huang, W., Liu, C. and Pu, H. (2020) Domain Knowledge Graph-Based Research Progress of Knowledge Representation. Neural Computing and Applications, 33, 681-690. https://doi.org/10.1007/s00521-020-05057-5
Yu, H., Li, H., Mao, D. and Cai, Q. (2020) A Relationship Extraction Method for Domain Knowledge Graph Construction. World Wide Web, 23, 735-753. https://doi.org/10.1007/s11280-019-00765-y
Kejriwal, M., Sequeda, J. and Lopez, V. (2019) Knowledge Graphs: Construction, Management and Que-rying. Semantic Web, 10, 961-962. https://doi.org/10.3233/sw-190370
Hogan, A. (2020) Resource Description Framework. In: Hogan, A., Ed., The Web of Data, Springer International Pub-lishing, 59-109. https://doi.org/10.1007/978-3-030-51580-5_3
Saccenti, R. (2022) Le molteplici stagioni del classico: Manoscritti e contenuti del De Interpretatione fra Boezio e Tommaso d’Aquino. Rivista di Storia Della Filosofia, 77, 238-272.
Gori, M. and Scarselli, F. (1998) Are Multilayer Perceptrons Adequate for Pattern Recognition and Verification? IEEE Transactions on Pat-tern Analysis and Machine Intelligence, 20, 1121-1132. https://doi.org/10.1109/34.730549