Abstract
The concept reasoning is an essential task in text data management and understanding. Recent methods usually capture shallow semantic features and cannot extend to multi-hop reasoning. Knowledge graphs have rich text information and connections. We use a knowledge graph to encode complex semantic relation between evidence and question. The nodes represent valuable information as clue entities and candidate answers in evidence and question, and the edges represent the reasoning rules between nodes.
In this paper, we propose a graph-based reasoning framework with iterative steps. The model obtains the completed evidence chain through iterative reasoning. The new approach iteratively infers the clue entities and candidate answers from the question and clue paragraphs to as new nodes to expand the semantic relation graph. Then we update the semantic representation of the questions and context via memory network and apply the graph attention network to encode the reasoning paths in the knowledge graph. Extensive experiments on commonsense reasoning and multi-hop question answering verified the advantage and improvements of the proposed approach.
This work was supported by NSFC grant 61972151.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Asai, A., Hashimoto, K., Hajishirzi, H., Socher, R., Xiong, C.: Learning to retrieve reasoning paths over Wikipedia graph for question answering. In: ICLR (2020)
Cao, N.D., Aziz, W., Titov, I.: Question answering by reasoning across documents with graph convolutional networks. In: NAACL, pp. 2306–2317 (2019)
Cao, Y., Fang, M., Tao, D.: BAG: bi-directional attention entity graph convolutional network for multi-hop reasoning question answering. In: NAACL-HLT, pp. 357–362 (2019)
Chen, D., Fisch, A., Weston, J., Bordes, A.: Reading Wikipedia to answer open-domain questions. In: ACL, pp. 1870–1879 (2017)
Das, R., Dhuliawala, S., Zaheer, M., McCallum, A.: Multi-step retriever-reader interaction for scalable open-domain question answering. In: ICLR (2019)
Dhingra, B., Jin, Q., Yang, Z., Cohen, W., Salakhutdinov, R.: Neural models for reasoning over multiple mentions using coreference. In: NAACL, pp. 42–48 (2018)
Ding, M., Zhou, C., Chen, Q., Yang, H., Tang, J.: Cognitive graph for multi-hop reading comprehension at scale. In: ACL 2019, pp. 2694–2703 (2019)
Fang, Y., Sun, S., Gan, Z., Pillai, R., Wang, S., Liu, J.: Hierarchical graph network for multi-hop question answering. CoRR abs/1911.03631 (2019)
Feldman, Y., El-Yaniv, R.: Multi-hop paragraph retrieval for open-domain question answering. In: ACL, pp. 2296–2309 (Jul 2019)
Kumar, A., et al.: Ask me anything: dynamic memory networks for natural language processing. In: ICML, pp. 1378–1387 (2016)
Lee, K., Chang, M., Toutanova, K.: Latent retrieval for weakly supervised open domain question answering. In: ACL, pp. 6086–6096 (2019)
Lin, B.Y., Chen, X., Chen, J., Ren, X.: KagNet: knowledge-aware graph networks for commonsense reasoning. In: Proceedings of EMNLP-IJCNLP (2019)
Lv, S., et al.: Graph-based reasoning over heterogeneous external knowledge for commonsense question answering. CoRR abs/1909.05311 (2019)
Qi, P., Lin, X., Mehr, L., Wang, Z., Manning, C.D.: Answering complex open-domain questions through iterative query generation. In: EMNLP-IJCNLP, pp. 2590–2602 (2019)
Rajani, N.F., McCann, B., Xiong, C., Socher, R.: Explain yourself! Leveraging language models for commonsense reasoning. In: ACL (2019)
Seo, M.J., Kembhavi, A., Farhadi, A., Hajishirzi, H.: Bidirectional attention flow for machine comprehension. In: ICLR (2017)
Shen, Y., Huang, P., Gao, J., Chen, W.: ReasoNet: learning to stop reading in machine comprehension. CoRR abs/1609.05284 (2016)
Sukhbaatar, S., Szlam, A., Weston, J., Fergus, R.: Weakly supervised memory networks. CoRR abs/1503.08895 (2015)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: ICLR, pp. 1–12 (2018)
Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: Cortes, C., Lawrence, N.D., Lee, D.D., Sugiyama, M., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 28, pp. 2692–2700. Curran Associates, Inc. (2015). http://papers.nips.cc/paper/5866-pointer-networks.pdf
Wang, W., Yang, N., Wei, F., Chang, B., Zhou, M.: Gated self-matching networks for reading comprehension and question answering. In: ACL, pp. 189–198 (2017)
Xiao, Y., et al.: Dynamically fused graph network for multi-hop reasoning (2019). arxiv:1905.06933Comment. Accepted by ACL 19
Yang, Z., Qi, P., Zhang, S., Bengio, Y., Cohen, W.W., Salakhutdinov, R., Manning, C.D.: HotpotQA: a dataset for diverse, explainable multi-hop question answering. In: EMNLP, pp. 2369–2380 (2018)
Yu, A.W., et al.: QANet: combining local convolution with global self-attention for reading comprehension. In: ICLR (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Xu, L., Yao, J. (2021). Iterative Reasoning over Knowledge Graph. In: Jensen, C.S., et al. Database Systems for Advanced Applications. DASFAA 2021. Lecture Notes in Computer Science(), vol 12681. Springer, Cham. https://doi.org/10.1007/978-3-030-73194-6_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-73194-6_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73193-9
Online ISBN: 978-3-030-73194-6
eBook Packages: Computer ScienceComputer Science (R0)