Abstract
Multi-hop knowledge graph question answering (KGQA) targets at pinpointing the answer entities to a natural language question by reasoning across multiple triples in knowledge graphs (KGs). When faced with multi-hop questions, existing methods take the whole relation paths into consideration, whereas the number of candidate paths grows exponentially with the increasement of path length, resulting in high search space complexity. Meanwhile, due to the complex semantic information, it is important to focus on different parts of the question at different steps. Moreover, previous studies only give the predicted answers but lack a relational path to indicate the reasoning process. To address these challenges, this paper proposes an interpretable neural model for multi-hop KGQA, namely Dynamic Reasoning Network (DRN). Inspired by human’s hop-by-hop reasoning behavior, DRN employs an interpretable, stepwise reasoning process to predict a relation at each step, all the intermediate relations form a traceable reasoning path. With effectively stepwise path search over KGs, DRN reduces the search space significantly. Furthermore, to facilitate semantic parsing, DRN dynamically updates the representation of relations and questions for each step based on attention mechanism. Extensive experiments conducted over four benchmark datasets from football, movie and general domain well demonstrate the effectiveness of our method.
Similar content being viewed by others
Data Availability
All the experimental datasets in this paper are public. In addition, the literature or website sources of the experimental data have been provided in the form of references or footnotes.
Code Availability
Code and deployment instructions are available upon request by the authors.
References
Das R, Dhuliawala S, Zaheer M, Vilnis L, Durugkar I, Krishnamurthy A, Smola A, McCallum A (2018) Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning. In: ICLR
Feng J, Wei Q, Cui J, Chen J (2022) Novel translation knowledge graph completion model based on 2d convolution. Appl Intell 52(3):3266–3275
Chen L, Cui J, Tang X, Qian Y, Li Y, Zhang Y (2022) Rlpath: a knowledge graph link prediction method using reinforcement learning based attentive relation path searching and representation learning. Appl Intell 52(4):4715–4726
Hua Y, Li Y, Qi G, Wu W, Zhang J, Qi D (2020) Less is more: Data-efficient complex question answering over knowledge bases. J Web Semant 65:100612
Li X, Alazab M, Li Q, Yu K, Yin Q (2021) Question-aware memory network for multi-hop question answering in human-robot interaction. Complex Intell Syst
Zhang R, Wang Y, Mao Y, Huai J (2019) Question answering in knowledge bases: A verification assisted model with iterative training. ACM Trans. Inf Syst 37(4):40–14026
Cui H, Peng T, Feng L, Bao T, Liu L (2021) Simple question answering over knowledge graph enhanced by question pattern classification. Knowl Inf Syst 63:2741–2761
Zhang Q, Weng X, Zhou G, Zhang Y, Huang JX (2022) ARL: An adaptive reinforcement learning framework for complex question answering over knowledge base. Inf Process Manag 59(3):102933
Zhu A, Ouyang D, Liang S, Shao J (2022) Step by step: a hierarchical framework for multi-hop knowledge graph reasoning with reinforcement learning. Knowl Based Syst 248:108843
Wu W, Zhu Z, Zhang G, Kang S, Liu P (2021) A reasoning enhance network for muti-relation question answering. Appl Intell 51(7):4515–4524
Lan Y, Wang S, Jiang J (2019) Multi-hop knowledge base question answering with an iterative sequence matching model. In: ICDM, pp 359–368
Yu M, Yin W, Hasan KS, dos Santos CN, Xiang B, Zhou B (2017) Improved neural relation detection for knowledge base question answering. In: ACL, pp 571–581
Zhang H, Xu G, Liang X, Huang T, Fu K (2018) An attention-based word-level interaction model: Relation detection for knowledge base question answering. arXiv:1801.09893
Lan Y, Wang S, Jiang J (2019) Knowledge base question answering with topic units. In: IJCAI, pp 5046–5052
Zhang Y, Dai H, Kozareva Z, Smola AJ, Song L (2018) Variational reasoning for question answering with knowledge graph. In: AAAI, pp 6069–6076
Zhou M, Huang M, Zhu X (2018) An interpretable reasoning network for multi-relation question answering. In: COLING, pp 2010–2022
Wang X, Zhao S, Han J, Cheng B, Yang H, Ao J, Li Z (2020) Modelling long-distance node relations for KBQA with global dynamic graph. In: COLING, pp 2572–2582
Han J, Cheng B, Wang X (2020) Two-phase hypergraph based reasoning with dynamic relations for multi-hop KBQA. In: IJCAI, pp 3615–3621
Sukhbaatar S, Szlam A, Weston J, Fergus R (2015) End-to-end memory networks. In: NIPS, pp 2440–2448
Miller AH, Fisch A, Dodge J, Karimi A, Bordes A, Weston J (2016) Key-value memory networks for directly reading documents. In: EMNLP, pp 1400–1409
Xu K, Lai Y, Feng Y, Wang Z (2019) Enhancing key-value memory neural networks for knowledge based question answering. In: NAACL-HLT, pp 2937–2947
Saxena A, Tripathi A, Talukdar PP (2020) Improving multi-hop question answering over knowledge graphs using knowledge base embeddings. In: ACL, pp 4498–4507
Li L, Zhang M, Chao Z, Xiang J (2021) Using context information to enhance simple question answering. World Wide Web 24(1):249–277
Ren H, Dai H, Dai B, Chen X, Yasunaga M, Sun H, Schuurmans D, Leskovec J, Zhou D (2021) LEGO: Latent execution-guided reasoning for multi-hop question answering on knowledge graphs. In: ICML, vol 139, pp 8959–8970
Hao Z, Chen J, Wen W, Wu B, Cai R (2022) Motif-based memory networks for complex-factoid question answering. Neurocomputing 485:12–21
Bakhshi M, Nematbakhsh M, Mohsenzadeh M, Rahmani AM (2022) Sparseqa: Sequential word reordering and parsing for answering complex natural language questions over knowledge graphs. Knowl Based Syst 235:107626
Chen Z, Chang C, Chen Y, Nayak J, Ku L (2019) Uhop: an unrestricted-hop relation extraction framework for knowledge-based question answering. In: NAACL, pp 345–356
Nishida K, Nishida K, Nagata M, Otsuka A, Saito I, Asano H, Tomita J (2019) Answering while summarizing: Multi-task learning for multi-hop QA with evidence extraction. In: ACL, pp 2335–2345
Qiu L, Xiao Y, Qu Y, Zhou H, Li L, Zhang W, Yu Y (2019) Dynamically fused graph network for multi-hop reasoning. In: ACL, pp 6140–6150
Lv X, Han X, Hou L, Li J, Liu Z, Zhang W, Zhang Y, Kong H, Wu S (2020) Dynamic anticipation and completion for multi-hop reasoning over sparse knowledge graph. In: EMNLP, pp 5694–5703
Shi J, Cao S, Hou L, Li J, Zhang H (2021) Transfernet: an effective and transparent framework for multi-hop question answering over relation graph. In: EMNLP, pp 4149–4158
Qin K, Wang Y, Li C, Gunaratna K, Jin H, Pavlu V, Aslam JA (2020) A complex kbqa system using multiple reasoning paths. arXiv:2005.10970
Qiu Y, Wang Y, Jin X, Zhang K (2020) Stepwise reasoning for multi-relation question answering over knowledge graph with weak supervision. In: WSDM, pp 474–482
He G, Lan Y, Jiang J, Zhao WX, Wen J (2021) Improving multi-hop knowledge base question answering by learning intermediate supervision signals. In: WSDM, pp 553–561
Sun H, Bedrax-Weiss T, Cohen WW (2019) Pullnet: Open domain question answering with iterative retrieval on knowledge bases and text. In: EMNLP, pp 2380–2390
Xiong W, Yu M, Chang S, Guo X, Wang WY (2019) Improving question answering over incomplete kbs with knowledge-aware reader. In: ACL, pp 4258–4264
Han J, Cheng B, Wang X (2020) Open domain question answering based on text enhanced knowledge graph with hyperedge infusion. In: EMNLP, pp 1475–1481
Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. In: ICLR
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. In: NIPS, pp 5998–6008
See A, Liu PJ, Manning CD (2017) Get to the point: Summarization with pointer-generator networks. In: ACL, pp 1073–1083
Zhang L, Winn JM, Tomioka R (2016) Gaussian attention model and its application to knowledge base embedding and question answering. arXiv:1611.02266
Han X, Cao S, Xin L, Lin Y, Liu Z, Sun M, Li J (2018) Openke: an open toolkit for knowledge embedding. In: EMNLP, pp 139–144
Funding
This work is supported by the National Natural Science Foundation of China under grant No.61872163 and 61806084, Jilin Province Key Scientific and Technological Research and Development Project under grant No.20210201131GX, and Jilin Provincial Education Department project under grant No.JJKH20190160KJ.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of Interest
The authors have no relevant financial or non-financial interests to disclose.
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 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.
About this article
Cite this article
Cui, H., Peng, T., Bao, T. et al. Stepwise relation prediction with dynamic reasoning network for multi-hop knowledge graph question answering. Appl Intell 53, 12340–12354 (2023). https://doi.org/10.1007/s10489-022-04127-6
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-022-04127-6