Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
SpringerLink
Log in

Improving embedded knowledge graph multi-hop question answering by introducing relational chain reasoning

  • Published:
Data Mining and Knowledge Discovery Aims and scope Submit manuscript

Abstract

Knowledge Graph Question Answering (KGQA) aims to answer user-questions from a knowledge graph (KG) by identifying the reasoning relations between topic entity and answer. As a complex branch task of KGQA, multi-hop KGQA requires reasoning over the multi-hop relational chain preserved in KG to arrive at the right answer. Despite recent successes, the existing works on answering multi-hop complex questions still face the following challenges: (i) The absence of an explicit relational chain order reflected in user-question stems from a misunderstanding of a user’s intentions. (ii) Incorrectly capturing relational types on weak supervision of which dataset lacks intermediate reasoning chain annotations due to expensive labeling cost. (iii) Failing to consider implicit relations between the topic entity and the answer implied in structured KG because of limited neighborhoods size constraint in subgraph retrieval-based algorithms. To address these issues in multi-hop KGQA, we propose a novel model herein, namely Relational Chain based Embedded KGQA (Rce-KGQA), which simultaneously utilizes the explicit relational chain revealed in natural language question and the implicit relational chain stored in structured KG. Our extensive empirical study on three open-domain benchmarks proves that our method significantly outperforms the state-of-the-art counterparts like GraftNet, PullNet and EmbedKGQA. Comprehensive ablation experiments also verify the effectiveness of our method on the multi-hop KGQA task. We have made our model’s source code available at github: https://github.com/albert-jin/Rce-KGQA.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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
Fig. 6
Fig. 7

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  • Abujabal, A., Yahya, M., Riedewald, M.: Automated template generation for question answering over knowledge graphs. In: Proceedings of the 26th International Conference on World Wide Web, pp. 1191–1200. International Conference on World Wide Web (2017)

  • Afzal, A., Sading, M., Hussain, M., Ali, M., Lee, S., Khattak, A.: Knowledge-based reasoning and recommendation framework for intelligent decision making. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pp. 571–581. Expert Systems (2018). https://doi.org/10.1111/exsy.12242

  • Alexander, H.M., Adam, F., Jesse, D., Amir-Hossein, K.: Key-value memory networks for directly reading documents, pp. 249–256. EMNLP (2016)

  • Alon, T., Jonathan, B.: The web as a knowledge-base for answering complex questions. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pp. 641–651. In NAACL-HLT (2018)

  • Ashish, V., Noam, S., Niki, P., Jakob, U., Llion, J., Gomez, A.N., Lukasz, K., Illia, P.: Attention Is All You Need (2017)

  • Bast, H., Haussmann, E.: More accurate question answering on freebase. In: Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, pp. 1431–1440 (2015)

  • Bill, Yuchen, L., Xinyue, C., Jamin, C., Xiang, R.: Kagnet: Knowledge-aware graph networks for commonsense reasoning, pp. 2829–2839. Association for Computational Linguistics (2019)

  • Bin, F., Yunqi, Q., Chengguang, T., Yang, L., Haiyang, Y., Jian, S.: A survey on complex question answering over knowledge base: recent advances and challenges. CoRR (2020)

  • Bordes, A., Usunier, N., Garcla-Duran, A., Weston, J., Yakhnenko, O.: Translating embeddings for modeling multi-relational data. In: Proceedings of Advance Neural Information Process, pp. 2787–2795 (2013)

  • Boris, G.: Question-answering system for teaching autistic children to reason about mental states. Technical report (2000)

  • Chen, Y., Subburathinam, A., Chen, C.-H., Zaki, M.J.: Personalized food recommendation as constrained question answering over a large-scale food knowledge graph. In: Proceedings of the 14th ACM International Conference on Web Search and Data Mining (2021)

  • Chopra, S., LeCun, Y.: Learning a similarity metric discriminatively with application to face verification. In: IEEE Computer Society Conference Computer Vision and Pattern Recognition, pp. 539–546 (2005)

  • Das, R., Godbole, A., Naik, A., Tower, E., Zaheer, M., Hajishirzi, H., Jia, R., Mccallum, A.: Knowledge base question answering by case-based reasoning over subgraphs. In: Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., Sabato, S. (eds.) Proceedings of the 39th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 162, pp. 4777–4793. PMLR, (2022)

  • Deepak, N., Jatin, C., Charu, S., Manohar, K.: Learning attention-based embeddings for relation prediction in knowledge graphs. In: Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, pp. 4710–4723 (2019)

  • Ding H, Huang S, Jin W, Shan Y, Yu H (2022) A novel cascade model for end-to-end aspect-based social comment sentiment analysis. Electronics. https://doi.org/10.3390/electronics11121810

    Article  Google Scholar 

  • Dong, L., Wei, F., Zhou, M., Xu, K.: Question answering over Freebase with multi-column convolutional neural networks, pp. 260–269. Association for Computational Linguistics, Beijing, China (2015)

  • Drew, A.H., Christopher, D.M.: Learning by abstraction: The neural state machine. In: NeurIPS, pp. 5901–5914 (2019)

  • Gao S, Chen X, Ren Z, Zhao D, Yan R (2021) Meaningful answer generation of e-commerce question-answering. ACM Trans Inf Syst. https://doi.org/10.1145/3432689

    Article  Google Scholar 

  • Gao J, Yu H, Zhang S (2022) Joint event causality extraction using dual-channel enhanced neural network. Knowl.-Based Syst. 258:109935. https://doi.org/10.1016/j.knosys.2022.109935

    Article  Google Scholar 

  • Glorot, Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, vol. 9, pp. 249–256. PMLR (2010)

  • Gu H, Yu H, Luo X (2022) Dbgare: Across-within dual bipartite graph attention for enhancing distantly supervised relation extraction. In: Memmi G, Yang B, Kong L, Zhang T, Qiu M (eds) Knowledge Science, Engineering and Management. Springer, Cham, pp 400–412

    Chapter  Google Scholar 

  • Haitan, S., Bhuwan, D., Manzil, Z., Kathryn, M., Ruslan, S., Cohen, W.W.: Open domain question answering using early fusion of knowledge bases and text (2018)

  • Haitan, S., Tania, B.-W., William, W.C.: Pullnet: Open domain question answering with iterative retrieval on knowledge bases and text, pp. 474–482. EMNLP (2019)

  • Hao, Y., Zhang, Y., Liu, K., Zhao, J.: An end-to-end model for question answering over knowledge base with cross-attention combining global knowledge, pp. 221–231. Association for Computational Linguistics, (2017)

  • He, G., Lan, Y., Jiang, J., Zhao, W.X., Wen, J.-R.: 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. WSDM ’21, pp. 553–561. Association for Computing Machinery, New York, NY, USA (2021). 10.1145/3437963.3441753

  • He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification (2015)

  • Huang H, Wei X, Nie L, Mao X, Xu X-S (2018) From question to text: question-oriented feature attention for answer selection. ACM Trans Inf Syst. https://doi.org/10.1145/3233771

    Article  Google Scholar 

  • Jain, S.: Question answering over knowledge-base using factual memory networks. In: NAACL (2016)

  • Jeffrey, P., Richard, S., Christopher, M.: Global vectors for word representation. In: In EMNLP, pp. 1532–1543 (2014)

  • Jin, W., Yu, H., Luo, X.: Cvt-assd: Convolutional vision-transformer based attentive single shot multibox detector. In: 2021 IEEE 33rd International Conference on Tools with Artificial Intelligence (ICTAI), pp. 736–744 (2021). https://doi.org/10.1109/ICTAI52525.2021.00117

  • Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: 5th International Conference on Learning Representations, pp. 486–490. ICLR, April 24-26 (2017)

  • Kun, X., Yuxuan, L., Yansong, F., Zhiguo, W.: Enhancing key-value memory neural networks for knowledge based question answering. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, pp. 2937–2947. Association for Computational Linguistics (2019)

  • LAN, Y., Jing, J.: Query graph generation for answering multi-hop complex questions from knowledge bases (2020)

  • Lan Y, Wang S, Jiang J (2019) Knowledge base question answering with a matching-aggregation model and question-specific contextual relations. IEEE/ACM Trans. Audio Speech Lang. Process. 27(10):1629–1638

    Article  Google Scholar 

  • Michael, P., Luke, Z.: Simplequestions nearly solved: a new upperbound and baseline approach. CoRR (2018)

  • Min-Chul, Y., Do-Gil, L., HaeChang, R.: Knowledge-based question answering using the semantic embedding space. In: Expert Systems with Applications, pp. 9086–9104 (2015)

  • Mo, Y., Wenpeng, Y., Kazi, S.H., Bowen, Z.: Improved neural relation detection for knowledge base question answering. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pp. 571–581. Association for Computational Linguistics (2017)

  • Molino P, Aiello LM, Lops P (2016) Social question answering: textual, user, and network features for best answer prediction. ACM Trans Inf Syst. https://doi.org/10.1145/2948063

    Article  Google Scholar 

  • Mueller, J., Thyagarajan, A.: Siamese recurrent architectures for learning sentence similarity. In: AAAI, pp. 2786–2792. Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence (2016)

  • Nickel, M., Rosasco, L., Poggio, T.: Holographic embeddings of knowledge graphs. In: Proceedings of 30th AAAI Conference 2016, pp. 1955–1961 (2016)

  • Nickel, N., Tresp, V., Kriegel, H.-P.: A three-way model for collective learning on multi-relational data. In: Proceeding of the 28th International Conference, pp. 809–816 (2011)

  • Ott, M., Edunov, S., Baevski, A., Fan, A., Gross, S., Ng, N., Grangier, D., Auli, M.: fairseq: A fast, extensible toolkit for sequence modeling. In: Proceedings of NAACL-HLT 2019: Demonstrations (2019)

  • Reid, A., Fan, R.K.C., Kevin, J.L.: Local graph partitioning using pagerank vectors. In: FOCS (2006)

  • Saxena, A., Tripathi, A., Talukdar, P.: Improving multi-hop question answering over knowledge graphs using knowledge base embeddings, pp. 4498–4507 (2020)

  • Sun Z, Wang C, Hu W, Chen M, Dai J, Zhang W, Qu Y (2020) Knowledge graph alignment network with gated multi-hop neighborhood aggregation 34:222–229

    Google Scholar 

  • Tao, Q., Luo, X., Wang, H., Xu, R.: Enhancing relation extraction using syntactic indicators and sentential contexts. In: 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), pp. 1574–1580 (2019). https://doi.org/10.1109/ICTAI.2019.00227

  • Tingting, J., Hao, W., Xiangfeng, L., Xie, S., Jingchao, W.: Mifas: Multi-source heterogeneous information fusion with adaptive importance sampling for link prediction (2021). https://doi.org/10.1111/exsy.12888

  • Trouillon, T., Welbl, J., Riedel, S., Gaussier, E., Bouchard, G.: Complex embeddings for simple link prediction. In: International Conference on Machine Learning, pp. 2071–2080 (2016)

  • Wang, R., Rossetto, L., Cochez, M., Bernstein, A.: QAGCN: A graph convolutional network-based multi-relation question answering system (2022). https://doi.org/10.48550/ARXIV.2206.01818

  • Wang, A., Zhang, J., Feng, J., Chen, Z.: Knowledge graph embedding by translating on hyperplanes. In: 28th AAAI, pp. 1112–1119 (2014)

  • Wang Q, Mao Z, Wang B, Guo L (2017) Knowledge graph embedding: a survey of approaches and applications. IEEE Trans. Knowl. Data Eng. 29(12):2724–2743

    Article  Google Scholar 

  • Wentau, Y., Matthew, R., Christopher, M., Ming-Wei, C., Jina, S.: The value of semantic parse labeling for knowledge base question answering. In: In ACL, pp. 2787–2795 (2016)

  • Xavier, G., Antoine, B., Yoshua, B.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, vol. 15, pp. 315–323 (2011)

  • Xia N, Yu H, Wang Y, Xuan J, Luo X (2022) Dafs: a domain aware few shot generative model for event detection. Mach Learn. https://doi.org/10.1007/s10994-022-06198-5

    Article  Google Scholar 

  • Xiao, H., Jingyuan, Z., Dingcheng, L., Ping, L.: Knowledge graph embedding based question answering, pp. 105–113. In: Proceedings of the 13th ACM International Conference on Web Search and Data Mining (2019)

  • Xiao, J., Kalia, A.K., Vukovic, M.: Juno: An intelligent chat service for it service automation. In: Service-Oriented Computing—ICSOC 2018 Workshops, pp. 486–490. Springer, Cham (2019)

  • Yao, X., Van, D.: Information extraction over structured data: question answering with freebase (2014)

  • Yinhan, L., Myle, O., Naman, G., Jingfei, D.: A robustly optimized bert pretraining approach: Roberta. PMLR (2019)

  • Yu H, Lu J, Zhang G (2020) An online robust support vector regression for data streams. IEEE Trans Knowl Data Eng. https://doi.org/10.1109/TKDE.2020.2979967

    Article  Google Scholar 

  • Yu H, Lu J, Zhang G (2020) Continuous support vector regression for nonstationary streaming data. IEEE Trans Cybern. https://doi.org/10.1109/TCYB.2020.3015266

    Article  Google Scholar 

  • Yunqi, Q., Yuanzhuo, Wang, X.J., Kun, Z.: Stepwise reasoning for multi-relation question answering over knowledge graph with weak supervision, pp. 474–482. WSDM (2020)

  • Yunshi, L., Gaole, H., Jinhao, J., Jing, J., Wayne, X., Jirong, W.: A survey on complex knowledge base question answering: methods, challenges and solutions. CoRR (2021)

  • Yunshi, L., Shuohang, W., Jing, J.: Knowledge base question answering with topic units. In: IJCAI (2019)

  • Yuyu, Z., Hanjun, D., Zornitsa, Kozareva, Alexander, J, S., Le, S.: Variational reasoning for question answering with knowledge grap. In: In Thirty-Second AAAI Conference on Artificial Intelligence, pp. 2787–2795 (2018)

  • Zhao Z, Yu H, Luo X, Gao J, Xu X, Shengming G (2022) Ia-icgcn: Integrating prior knowledge via intra-event association and inter-event causality for chinese causal event extraction. In: Pimenidis E, Angelov P, Jayne C, Papaleonidas A, Aydin M (eds) Artificial Neural Networks and Machine Learning - ICANN 2022. Springer, Cham, pp 519–531

    Chapter  Google Scholar 

  • Zi-Yuan, C., Chih-Hung, C., Lun-Wei, K.: Uhop: An unrestricted-hop relation extraction framework for knowledge-based question answering. In: NAACL (2019)

Download references

Acknowledgements

This work was partially supported by the Shanghai Yangfan Program (Project Code: 22YF1413600), the Major Research Plan of National Natural Science Foundation of China (Project Code: 92167102), and the Shaanxi Province Key Industrial Chain Projects (Project Code: NO.2018ZDCXL-GY-04-03-02). The authors would like to thank Guizhong Liu and Ruiping Yin for providing helpful discussions and comments.

Author information

Authors and Affiliations

  1. School of Information and Communications Engineering, Xi’an Jiaotong University, Xi’an, 710049, Shaanxi, China

    Weiqiang Jin, Biao Zhao & Guizhong Liu

  2. School of Computer Engineering and Science, Shanghai University, Baoshan, Shanghai, 200444, China

    Hang Yu & Xi Tao

  3. Information Faculty of Computer School, Beijing University of Technology, Chaoyang, Beijing, 100124, China

    Ruiping Yin

  4. Engineering Research Center of Intelligence Perception and Autonomous Control, Ministry of Education, Beijing, 100124, China

    Ruiping Yin

Authors
  1. Weiqiang Jin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Biao Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hang Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xi Tao
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Ruiping Yin
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Guizhong Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hang Yu.

Additional information

Responsible editor: Tim Weninger.

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

Jin, W., Zhao, B., Yu, H. et al. Improving embedded knowledge graph multi-hop question answering by introducing relational chain reasoning. Data Min Knowl Disc 37, 255–288 (2023). https://doi.org/10.1007/s10618-022-00891-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10618-022-00891-8

Keywords

Search

Navigation