Skip to main content
SpringerLink
Log in

Knowledge-aware adaptive graph network for commonsense question answering

  • Research
  • Published:
Journal of Intelligent Information Systems Aims and scope Submit manuscript

Abstract

Commonsense Question Answering (CQA) aims to select the correct answers to common knowledge questions. Most existing approaches focus on integrating external knowledge graph (KG) representations with question context representations to facilitate reasoning. However, the approaches cannot effectively select the correct answer due to (i) the incomplete reasoning chains when using knowledge graphs as external knowledge, and (ii) the insufficient understanding of semantic information of the question during the reasoning process. Here we propose a novel model, KA-AGN. First, we utilize a joint representation of dependency parse trees and language models to describe QA pairs. Next, we introduce question semantic information as nodes into a knowledge subgraph and compute the correlations between nodes using adaptive graph networks. Finally, bidirectional attention and graph pruning are employed to update the question representation and the knowledge subgraph representation. To evaluate the performance of our method, we conducted experiments on two widely used benchmark datasets: CommonsenseQA and OpenBookQA. The ablation experiment results demonstrate the effectiveness of the adaptive graph network in enhancing reasoning chains, while showing the ability of the joint representation of dependency parse trees and language models to correctly understand question semantics. Our code is publicly available at https://github.com/agfsghfdhg/KAAGN-main.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Data Availability

All the datasets gathered from other sources has been publicly available.

References

  • Abujabal, A., Yahya, M., Riedewald, M., et al. (2017). Automated template generation for question answering over knowledge graphs. In: proceedings of the 26th international conference on world wide web. International World Wide Web Conferences Steering Committee, 1191–1200. https://doi.org/10.1145/3038912.3052583.

  • Clark, P., Etzioni, O., Khashabi, D., et al. (2019). From ’f’ to ’a’ on the n.y. regents science exams: an overview of the aristo project. AI Magazine, 39–53. https://api.semanticscholar.org/CorpusID:202539605.

  • Cui, H., Peng, T., Bao, T., et al. (2022). Stepwise relation prediction with dynamic reasoning network for multi-hop knowledge graph question answering. Applied Intelligence, 12340–12354. https://api.semanticscholar.org/CorpusID:252550919.

  • Das, R., Godbole, A., Naik, A., et al. (2022). Knowledge base question answering by case-based reasoning over subgraphs. In: Chaudhuri K, Jegelka S, Song L, et al. (eds) proceedings of the 39th international conference on machine learning, Proceedings of Machine Learning Research, 4777–4793. https://proceedings.mlr.press/v162/das22a.html.

  • Ding, J., Hu, W., Xu, Q., et al. (2019). Leveraging frequent query substructures to generate formal queries for complex question answering. In: Inui K, Jiang J, Ng V, et al. (eds) proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, 2614–2622. https://doi.org/10.18653/v1/D19-1263.

  • Ding, Z., Li, Z. X., Qi, R., et al. (2023). Forecasttkgquestions: a benchmark for temporal question answering and forecasting over temporal knowledge graphs. In: International Semantic Web Conference. https://api.semanticscholar.org/CorpusID:259991877.

  • Dong, J., Zhang, Q., Huang, X., et al. (2023). Hierarchy-aware multi-hop question answering over knowledge graphs. In: proceedings of the ACM web conference 2023. Association for Computing Machinery, New York, NY, USA, WWW ’23, 2519–2527. https://doi.org/10.1145/3543507.3583376.

  • Du, C., Li, X., & Li, Z. (2024). Semantic-enhanced reasoning question answering overtemporal knowledge graphs. Journal of Intelligent Information Systems. https://doi.org/10.1007/s10844-024-00840-5

    Article  Google Scholar 

  • Feng, Y., Chen, X., Lin, B.Y., et al. (2020). Scalable multi-hop relational reasoning for knowledge-aware question answering. In: proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP). Association for Computational Linguistics, Online, 1295–1309. https://doi.org/10.18653/v1/2020.emnlp-main.99.

  • Ge, D., Li, J., & Zhu, M. (2019). A transformer-based semantic parser for nlpcc-2019 shared task 2. In: Springer-Verlag, 772–781. https://doi.org/10.1007/978-3-030-32236-6_70.

  • Gu, T., Zhao, H., He, Z., et al. (2023). Integrating external knowledge into aspect-based sentiment analysis using graph neural network. Knowledge-Based Systems, 259, 110025. https://doi.org/10.1016/j.knosys.2022.110025

    Article  Google Scholar 

  • Han, J., Cheng ,B., & Wang, X. (2020). Open domain question answering based on text enhanced knowledge graph with hyperedge infusion. In: findings of the association for computational linguistics: EMNLP 2020. Association for Computational Linguistics, Online, 1475–1481. https://doi.org/10.18653/v1/2020.findings-emnlp.133.

  • He, G., Lan, Y., Jiang, J., 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 ’21,553–561. https://doi.org/10.1145/3437963.3441753.

  • Kipf, T., & Welling, M. (2016) Semi-supervised classification with graph convolutional networks. arXiv:1609.02907. https://api.semanticscholar.org/CorpusID:3144218.

  • Lee, J., Lee, I., & Kang, J. (2019) Self-attention graph pooling. In: International conference on machine learning, PMLR, 3734–3743. https://api.semanticscholar.org/CorpusID:119314157.

  • Li R, Wang S, Zhu F., et al. (2018). Adaptive graph convolutional neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence,https://doi.org/10.1609/aaai.v32i1.11691.

  • Liang, B., Su, H., Gui, L., et al. (2022). Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks. Knowledge-Based Systems, 235, 107643. https://doi.org/10.1016/j.knosys.2021.107643

    Article  Google Scholar 

  • Liang, S., Wei, W., Mao, XL., et al. (2022b) BiSyn-GAT+: bi-syntax aware graph attention network for aspect-based sentiment analysis. In: findings of the association for computational linguistics: ACL 2022. Association for Computational Linguistics, Dublin, Ireland, 1835–1848. https://doi.org/10.18653/v1/2022.findings-acl.144.

  • Lin, B.Y., Chen, X., Chen, J., et al. (2019). KagNet: knowledge-aware graph networks for commonsense reasoning. In: proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, 2829–2839. https://doi.org/10.18653/v1/D19-1282.

  • Ma, T., Lv, S., Huang, L., et al. (2021). Hiam: a hierarchical attention based model for knowledge graph multi-hop reasoning. Neural Networks, 143, 261–270. https://doi.org/10.1016/j.neunet.2021.06.008

    Article  PubMed  Google Scholar 

  • Mihaylov, T., Clark, P., Khot, T., et al. (2018). Can a suit of armor conduct electricity? a new dataset for open book question answering. In: proceedings of the 2018 conference on empirical methods in natural language processing. Association for Computational Linguistics, Brussels, Belgium, 2381–2391. https://doi.org/10.18653/v1/D18-1260.

  • Park, J., Choi, H. K., Ko, J., et al. (2023). Relation-aware language-graph transformer for question answering. Proceedings of the AAAI Conference on Artificial Intelligence, 37(11), 13457–13464. https://doi.org/10.1609/aaai.v37i11.26578

    Article  Google Scholar 

  • Qiao, Z., Ye, W., Zhang, T., et al. (2022). Exploiting hybrid semantics of relation paths for multi-hop question answering over knowledge graphs. In: proceedings of the 29th international conference on computational linguistics. International Committee on Computational Linguistics, 1813–1822. https://aclanthology.org/2022.coling-1.156.

  • 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. Association for Computational Linguistics, Online, 4498–4507. https://doi.org/10.18653/v1/2020.acl-main.412.

  • Scarselli, F., Gori, M., Tsoi, A. C., et al. (2009). The graph neural network model. IEEE Transactions on Neural Networks, 20(1), 61–80. https://doi.org/10.1109/TNN.2008.2005605

    Article  PubMed  Google Scholar 

  • Schlichtkrull, M., Kipf, TN., Bloem, P., et al. (2018). Modeling relational data with graph convolutional networks. In: Springer-Verlag, Berlin, Heidelberg, 593–607. https://doi.org/10.1007/978-3-319-93417-4_38.

  • Shen, T., Geng, X., Qin, T., et al. (2019). Multi-task learning for conversational question answering over a large-scale knowledge base. In: proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP). Association for Computational Linguistics, 2442–2451. https://doi.org/10.18653/v1/D19-1248.

  • Speer, R., Chin, J., & Havasi, C. (2017). Conceptnet 5.5: an open multilingual graph of general knowledge. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. AAAI Press, 4444–4451. https://doi.org/10.1609/aaai.v31i1.11164.

  • Sun, H., Bedrax-Weiss, T., & Cohen, W. (2019a). PullNet: open domain question answering with iterative retrieval on knowledge bases and text. In: proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP). Association for Computational Linguistics, 2380–2390. https://doi.org/10.18653/v1/D19-1242.

  • Sun, K., Zhang, R., Mensah, S., et al. (2019b). Aspect-level sentiment analysis via convolution over dependency tree. In: proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP). Association for Computational Linguistics, 5679–5688. https://doi.org/10.18653/v1/D19-1569.

  • 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 2022 conference of the north american chapter of the association for computational linguistics: human language technologies. Association for Computational Linguistics, 5049–5060. https://doi.org/10.18653/v1/2022.naacl-main.372.

  • Talmor, A., Herzig, J., Lourie, N., et al. (2019). CommonsenseQA: a question answering challenge targeting commonsense knowledge. In: proceedings of the 2019 conference of the north american chapter of the association for computational linguistics: human language technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, 4149–4158. https://doi.org/10.18653/v1/N19-1421.

  • Thambi, S. V., & Raj, P. C. R. (2024). A novel technique using graph neural networks and relevance scoring to improve the performance of knowledge graph-based question answering systems. Journal of Intelligent Information Systems. https://doi.org/10.1007/s10844-023-00839-4

    Article  Google Scholar 

  • Tiddi, I., & Schlobach, S. (2021). Knowledge graphs as tools for explainable machine learning: a survey. Artificial Intelligence, 302, 103627. https://api.semanticscholar.org/CorpusID:239954152.

  • Undorf, M., Livneh, I., & Ackerman, R. (2021). Metacognitive control processes in question answering: help seeking and withholding answers. Metacognition and Learning, 16(2), 431–458. https://doi.org/10.1007/s11409-021-09259-7

    Article  Google Scholar 

  • Velickovic, P., Cucurull, G., Casanova, A., et al. (2017). Graph attention networks. arXiv:1710.10903. https://api.semanticscholar.org/CorpusID:3292002.

  • Wang, J., Li, X., & An, X. (2022). Modeling multiple latent information graph structures via graph convolutional network for aspect-based sentiment analysis. Complex & Intelligent Systems, 9, 4003–4014. https://api.semanticscholar.org/CorpusID:254810939.

  • Wang, X., Kapanipathi, P., Musa, R., et al. (2019). Improving natural language inference using external knowledge in the science questions domain. In: Proceedings of the AAAI Conference on Artificial Intelligence, 7208–7215. https://doi.org/10.1609/aaai.v33i01.33017208.

  • Wang, X., Li, Y., Wang, H., et al. (2023). Mkbqa: question answering over knowledge graph based on semantic analysis and priority marking method. Applied Sciences, 13(10). https://doi.org/10.3390/app13106104.

  • Xiong, W., Yu, M., Chang, S., et al. (2019) Improving question answering over incomplete KBs with knowledge-aware reader. In: proceedings of the 57th annual meeting of the association for computational linguistics. Association for Computational Linguistics, Florence, Italy, 4258–4264. https://doi.org/10.18653/v1/P19-1417.

  • Xu, B., Shen, H., Cao, Q., et al. (2019). Graph wavelet neural network. arXiv:1904.07785. https://api.semanticscholar.org/CorpusID:59279266.

  • Yasunaga, M., Ren, H., Bosselut, A., et al. (2021). QA-GNN: reasoning with language models and knowledge graphs for question answering. In: proceedings of the 2021 conference of the north american chapter of the association for computational linguistics: human language technologies. Association for Computational Linguistics, Online, 535–546. https://doi.org/10.18653/v1/2021.naacl-main.45.

  • Zhang, J., Shi, X., Xie, J., et al. (2018). Gaan: gated attention networks for learning on large and spatiotemporal graphs. In: Conference on Uncertainty in Artificial Intelligence,https://api.semanticscholar.org/CorpusID:3973810.

  • Zhang, M., Zhang, R., Zou, L., et al. (2021). NAMER: a node-based multitasking framework for multi-hop knowledge base question answering. In: proceedings of the 2021 conference of the north american chapter of the association for computational linguistics: human language technologies: demonstrations. Association for Computational Linguistics, Online, 18–25. https://doi.org/10.18653/v1/2021.naacl-demos.3.

  • Zhou, J., Cui, G., Hu, S., et al. (2020). Graph neural networks: a review of methods and applications. AI Open, 57–81,. https://doi.org/10.1016/j.aiopen.2021.01.001

  • Zhu, P., Yuan, Y., & Chen, L. (2023). Electra-based graph network model for multi-hop question answering. Journal of Intelligent Information Systems, 61, 819–834. https://doi.org/10.1007/s10844-023-00800-5

    Article  Google Scholar 

  • Zhuang, L., Wayne, L., Ya, S., et al. (2021) A robustly optimized BERT pre-training approach with post-training. In: proceedings of the 20th Chinese National conference on computational linguistics. Chinese Information Processing Society of China, 1218–1227. https://aclanthology.org/2021.ccl-1.108.

Download references

Acknowledgements

The authors would like to thank the anonymous reviewers for their helpful reviews.

Funding

This study received no funding.

Author information

Authors and Affiliations

  1. College of Computer Science, Xi’an University of Posts and Telecommunications, 618 West Chang’an Street, Shaanxi, 710121, China

    Long Kang, Xiaoge Li & Xiaochun An

  2. Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing, 618 West Chang’an Street, Shaanxi, 710121, China

    Long Kang, Xiaoge Li & Xiaochun An

  3. Xi’an Key Laboratory of Big Data and Intelligent Computing, 618 West Chang’an Street, Shaanxi, 710121, China

    Long Kang & Xiaoge Li

Authors
  1. Long Kang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaoge Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xiaochun An
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

The first author made the most significant contribution. The others contributed equally.

Corresponding author

Correspondence to Xiaoge Li.

Ethics declarations

Competing interests

The authors declare that there are no competing interests with anybody or any institution regarding the publication of this paper.

Ethical Approval and Consent to participate

Not Applicable.

Consent for publication

Not Applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kang, L., Li, X. & An, X. Knowledge-aware adaptive graph network for commonsense question answering. J Intell Inf Syst (2024). https://doi.org/10.1007/s10844-024-00854-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10844-024-00854-z

Keyword

Search

Navigation