research-article

A novel technique using graph neural networks and relevance scoring to improve the performance of knowledge graph-based question answering systems

Authors:

Sincy V. Thambi,

P. C. Reghu RajAuthors Info & Claims

Journal of Intelligent Information Systems, Volume 62, Issue 3

Pages 809 - 832

https://doi.org/10.1007/s10844-023-00839-4

Published: 22 January 2024 Publication History

Abstract

A Knowledge Graph-based Question Answering (KGQA) system attempts to answer a given natural language question using a knowledge graph (KG) rather than from text data. The current KGQA methods attempt to determine whether there is an explicit relationship between the entities in the question and a well-structured relationship between them in the KG. However, such strategies are difficult to build and train, limiting their consistency and versatility. The use of language models such as BERT has aided in the advancement of natural language question answering. In this paper, we present a novel Graph Neural Network(GNN) based approach with relevance scoring for improving KGQA. GNNs use the weight of nodes and edges to influence the information propagation while updating the node features in the network. The suggested method comprises subgraph construction, weighing of nodes and edges, and pruning processes to obtain meaningful answers. BERT-based GNN is used to build subgraph node embeddings. We tested the influence of weighting for both nodes and edges and observed that the system performs better for weighted graphs than unweighted graphs. Additionally, we experimented with several GNN convolutional layers and obtainined improved results by combining GENeralised Graph Convolution (GENConv) with node weights for simple questions. Extensive testing on benchmark datasets confirmed the effectiveness of the proposed model in comparison to state-of-the-art KGQA systems.

References

[1]

Bai, Y., Lv, X., et al. (2023). Answering complex logical queries on knowledge graphs via query computation tree optimization. JMLR.org, ICML’23, https://dl.acm.org/doi/10.5555/3618408.3618470

[2]

Bordes, A., Usunier, N., et al. (2015). Large–scale simple question answering with memory networks. CoRR abs/1506.02075. arXiv:1506.02075

[3]

Daniel, J., & James, M. (2019). Speech and Language Processing: An Introduction to Natural Language Processing. Computational Linguistics and Speech Recognition. 3rd Edition Draft. Prentice Hall, New Jersey., Chapter 25

[4]

Devlin J, Chang MW, et al. (2019) Bert: Pre–training of deep bidirectional transformers for language understanding. In: North American Chapter of the ACL, https://api.semanticscholar.org/CorpusID:52967399

[5]

Feng, Y., Chen, X., et al. (2020). Scalable multi-hop relational reasoning for knowledge-aware question answering. In: Proceedings of the 2020 Conference EMNLP. ACL, Online, pp 1295–1309,

[6]

Hamilton WL Graph representation learning Synthesis Lectures on Artificial Intelligence and Machine Learning 2020 14 3 1-159

[7]

Hao, C., Xie, M., et al. (2022). ACENet: Attention guided commonsense reasoning on hybrid knowledge graph. In: Proceedings of the Conference on EMNLP. ACL, Abu Dhabi, UAE, pp. 8461–8471,

[8]

He, G., Lan, Y., et al. (2021). Improving multi-hop knowledge base question answering by learning intermediate supervision signals. In: Proceedings of the 14th ACM International Conference on Web Search and Data Mining. Association for Computing Machinery, WSDM ’21, p 553–561,

Digital Library

[9]

Hogan, A., Blomqvist, et al. (2021). Knowledge graphs. ACM Comput Surv54(4).

Digital Library

[10]

Huang, X., Zhang, J., et al. (2019). Knowledge graph embedding based question answering. In: Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, WSDM ’19, pp. 105–113,

Digital Library

[11]

Huertas, G., Alvaro, et al. (2023). Exploring dimensionality reduction techniques in multilingual transformers. Cognitive Computation,15(2), 590–612.

[12]

Ji S, Pan S, et al. A survey on knowledge graphs: Representation, acquisition, and applications IEEE Transactions on Neural Networks and Learning Systems 2022 33 2 494-514

[13]

Jin W, Zhao B, et al. Improving embedded knowledge graph multi-hop question answering by introducing relational chain reasoning Data Mining and Knowledge Discovery 2023 37 1 255-288

Digital Library

[14]

Kingma DP and Ba J Bengio Y and LeCun Y Adam: A method for stochastic optimization 3rd International Conference on Learning Representations 2015 ICLR

[15]

Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations, https://openreview.net/forum?id=SJU4ayYgl

[16]

Kwok, C. C. T., Etzioni, O., & Weld, D. S. (2001). Scaling question answering to the web. In: Proceedings of the 10th International Conference on World Wide Web. Association for Computing Machinery, New York, NY, USA, WWW ’01, p 150–161,

Digital Library

[17]

Li G, Xiong C, Thabet AK, et al (2020) Deepergcn: All you need to train deeper gcns. arXiv:2006.07739. https://api.semanticscholar.org/CorpusID:219687460

[18]

Ma R, Han X, et al. Modeling and querying temporal rdf knowledge graphs with relational databases J Intell Inf Syst 2023 61 569-609

Digital Library

[19]

Maćkiewicz A and Ratajczak W Principal components analysis (pca) Computers & Geosciences 1993 19 3 303-342

Digital Library

[20]

Miller, A., Fisch, A., et al. (2016). Key–value memory networks for directly reading documents. In: Proceedings of the 2016 Conference on EMNLP. ACL, pp. 1400–1409.

[21]

Mital, P., Agarwal, S., Neti, B., et al. (2018). Graph based question answering system. CoRR abs/1812.01828. arXiv:1812.01828

[22]

Peng Z, Yu H, et al. Path-based reasoning with k-nearest neighbor and position embedding for knowledge graph completion J Intell Inf Syst 2022 58 513-533

Digital Library

[23]

Qiu, Y., Wang, Y., Jin, X., et al. (2020) Stepwise reasoning for multi-relation question answering over knowledge graph with weak supervision. In: Proceedings of the 13th International Conference on Web Search and Data Mining. Association for Computing Machinery, pp. 474–482,

Digital Library

[24]

Sacenti JAP and Rea Fileto Knowledge graph summarization impacts on movie recommendations J Intell Inf Syst 2022 58 43-66

Digital Library

[25]

Saxena, A., Tripathi, A., & Talukdar, P. (2020). Improving multi-hop question answering over knowledge graphs using knowledge base embeddings. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Online, pp 4498–4507, https://doi.org/10.18653/v1/2020.acl-main.412

[26]

Scarselli F, Gori M, et al. The graph neural network model IEEE Transactions on Neural Networks 2009 20 1 61-80

Digital Library

[27]

Schlichtkrull, M., Kipf, T. N., Bloem, P., et al. (2018). Modeling relational data with graph convolutional networks. In: The Semantic Web. Springer International Publishing, Cham, pp. 593–607,

Digital Library

[28]

Sen, P., Oliya, A., Saffari, A. (2021). Expanding end-to-end question answering on differentiable knowledge graphs with intersection. In: Proceedings of the Conference on EMNLP. ACL, pp. 8805–8812,

[29]

Shi, J., Cao, S., et al. (2021). TransferNet: An effective and transparent framework for multi-hop question answering over relation graph. In: Proceedings of the Conference on EMNLP, pp. 4149–4158,

[30]

Shi, Y., Huang, Z., et al. (2020). Masked label prediction: Unified massage passing model for semi-supervised classification. CoRR abs/2009.03509. arXiv:2009.03509

[31]

Sun, H., Dhingra, B., et al. (2018). Open domain question answering using early fusion of knowledge bases and text. In: Proceedings of the 2018 Conference on EMNLP. ACL, pp. 4231–4242,

[32]

Sun, H., Bedrax, T., et al. (2019). PullNet: Open domain question answering with iterative retrieval on knowledge bases and text. In: Proceedings of the Conference on EMNLP and the 9th IJCNLP, pp. 2380–2390,

[33]

Sun, Y., Shi, Q., Qi, L., et al. (2022). JointLK: Joint reasoning with language models and knowledge graphs for commonsense question answering. In: Proceedings of the Conference of the North American Chapter of the ACL: Human Language Technologies, pp. 5049–5060,

[34]

Thambi, S. V., & ReghuRaj, P. C. (2022a). Graph based document model and its application in keyphrase extraction. In: IEEE SPICES, pp 92–98,

[35]

Thambi, S. V., & ReghuRaj, P. C. (2022b). Towards improving the performance of question answering system using knowledge graph - a survey. In: Second ICAIS), pp 672–679,

[36]

Unger, C., Bühmann, L., Lehmann, J., et al. (2012). Template-based question answering over rdf data. In: Proceedings of the 21st International Conference on World Wide Web. Association for Computing Machinery, New York, NY, USA, WWW ’12, p 639–648,

Digital Library

[37]

Vashishth, S., Sanyal, S., et al. (2020). Composition-based multi-relational graph convolutional networks. In: ICLR. OpenReview.net, http://dblp.uni-trier.de/db/conf/iclr/iclr2020.html#VashishthSNT20

[38]

Wang, X., Luo, M., Si, C., et al. (2022a). Answering complex questions on knowledge graphs. In: Knowledge Science, Engineering and Management. Springer International Publishing, Cham, pp. 187–200,

Digital Library

[39]

Wang, Y., Yasunaga, M., Ren, H., et al. (2022b). Vqa-gnn: Reasoning with multimodal semantic graph for visual question answering. arXiv:2205.11501. https://api.semanticscholar.org/CorpusID:263895473

[40]

Wu G, He Y, and Hu X Entity linking: An issue to extract corresponding entity with knowledge base IEEE Access 2018 6 6220-6231

[41]

Xie, M., Hao, C., & Zhang, P. (2022). A sequential flow control framework for multi-hop knowledge base question answering. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, pp. 8450–8460,

[42]

Yasunaga, M., Ren, H., et al. (2021). QA-GNN: Reasoning with language models and knowledge graphs for question answering. In: Proceedings of the North American Chapter of the ACL: Human Language Technologies, pp 535–546,

[43]

Yu, X., Liang, D., & Li, Q. (2023). Improved graphsvx for gnn explanations based on cross entropy. In: 2023 4th International Conference on Electronic Communication and Artificial Intelligence (ICECAI), pp. 147–152,

[44]

Zhang, Y., Dai, H., Kozareva, Z., et al. (2018). Variational reasoning for question answering with knowledge graph. In: Proceedings of the 32 AAAI Conference on Artificial Intelligence, https://dl.acm.org/doi/pdf/10.5555/3504035.3504780

Cited By

Kang LLi XAn X(2024)Knowledge-aware adaptive graph network for commonsense question answeringJournal of Intelligent Information Systems10.1007/s10844-024-00854-z62:5(1305-1324)Online publication date: 1-Oct-2024
https://dl.acm.org/doi/10.1007/s10844-024-00854-z
Cao SZhu XLi P(2024)A Knowledge Graph Question Answering Approach Based on Graph Attention Networks and Relational Path EncodingAdvanced Intelligent Computing Technology and Applications10.1007/978-981-97-5669-8_7(77-89)Online publication date: 5-Aug-2024
https://dl.acm.org/doi/10.1007/978-981-97-5669-8_7

Recommendations

JPEC: A Novel Graph Neural Network for Competitor Retrieval in Financial Knowledge Graphs
SIGIR '24: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval

Knowledge graphs have gained popularity for their ability to organize and analyze complex data effectively. When combined with graph embedding techniques, such as graph neural networks (GNNs), knowledge graphs become a potent tool in providing valuable ...
Edge Based Graph Neural Network to Recognize Semigraph Representation of English Alphabets
MIKE 2013: Proceedings of the First International Conference on Mining Intelligence and Knowledge Exploration - Volume 8284

Graph Neural Network based on edges is introduced in this paper and is used to recognize the English uppercase alphabets treating their corresponding graphs as semigraphs. Graph Neural Network(GNN) is a connectionist model comprising of two feedforward ...
Meta-path reasoning of knowledge graph for commonsense question answering
Abstract
Commonsense question answering (CQA) requires understanding and reasoning over QA context and related commonsense knowledge, such as a structured Knowledge Graph (KG). Existing studies combine language models and graph neural networks to model ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Journal of Intelligent Information Systems

Journal of Intelligent Information Systems Volume 62, Issue 3

Jun 2024

275 pages

Issue’s Table of Contents

© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Publisher

Kluwer Academic Publishers

United States

Publication History

Published: 22 January 2024

Accepted: 29 December 2023

Revision received: 29 December 2023

Received: 25 August 2023

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

2
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 29 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Kang LLi XAn X(2024)Knowledge-aware adaptive graph network for commonsense question answeringJournal of Intelligent Information Systems10.1007/s10844-024-00854-z62:5(1305-1324)Online publication date: 1-Oct-2024
https://dl.acm.org/doi/10.1007/s10844-024-00854-z
Cao SZhu XLi P(2024)A Knowledge Graph Question Answering Approach Based on Graph Attention Networks and Relational Path EncodingAdvanced Intelligent Computing Technology and Applications10.1007/978-981-97-5669-8_7(77-89)Online publication date: 5-Aug-2024
https://dl.acm.org/doi/10.1007/978-981-97-5669-8_7

View Options

View options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Issue’s Table of Contents