Abstract
Multi-relation Question Answering is an important task of knowledge base over question answering (KBQA), multi-relation means that the question contains multiple relations and entity information, so it needs to use the fact triples in the knowledge base to analyze and reasoning the question in more detail. In this paper, we propose a novel model called Reasoning Enhance Network that uses context information, enhance the accuracy of relation and entity predicted in each hop. The model obtains the relation by analyzing the context information before each hop start, and then reasons the answer by the previous information; update question representation and reasoning state through predicted relation and entity, then promote the next hop reasoning starts. Our experiments clearly show that our method achieves good results on four datasets. Also, since we use attention mechanisms, our method offers better interpretability.
Similar content being viewed by others
References
Auer S, Bizer C, Kobilarov G, Lehmann J, Cyganiak R, Ives Z (2007) Dbpedia: A nucleus for a web of open data. In: The semantic web. Springer, pp 722–735
Google (2018) Freebase data dumps. https://developers.google.com/freebase. 27:386–393
Michael Sintek SD (2002) Triple—a query, inference, and transformation language for the semantic web
Xu K, Reddy S, Feng Y, Huang S, Zhao D (2016) Question answering on freebase via relation extraction and textual evidence. In: proceedings of the 54th annual meeting of the as sociation for computational linguistics, ACL 2016, vol 1, Long Papers, Berlin
Bast H, Haussmann E (2015) More Accurate question answering on freebase. In: proceedings of the 24th ACM international conference on information and knowledge management, CIKM 2015, vol 23, Melbourne, pp 1431–1440
Bordes A, Usunier N, Chopra S, Weston J (2015) Large-scale simple question answering with memory networks. CoRR, arXiv:1506.02075
Bordes A, Weston J, Usunier N (2014b) Open question answering with weakly supervised embedding models. In: Proceedings of ECML-PKDD, pp 165–180
Bordes A, Usunier N, Garcia-Duran A, Weston J, Yakhnenko O (2013) Translating embeddings for modeling multi -relational data. In: annual conference on neural information processing systems, pp 2787–2795
Miller A, Fisch A, Dodge J, Karimi A-H, Bordes A, Weston J (2016) Key-value memory networks for directly reading documents. In: Empirical Methods in Natural Language Processing, pp 1400–1409
Yih SW-t, Chang M-W, He X, Gao J (2015) Semantic parsing via staged query graph generation: Question answering with knowledge base. In: ACL, pp 1321–1331
Abujabal A, Yahya M, Riedewald M, Weikum G (2017) Automated template generation for question answering over knowledge graphs. In: WWW, pp 1191–1200
Wong YW, Mooney R (2007) Learning synchronous grammars for semantic parsing with lambda calculus. In: ACL, pp 960–967
Abujabal A, Yahya M, Riedewald M, Weikum G (2017) Automated template generation for question answering over knowledge graphs. In: WWW, pp 1191–1200
Hu S, Zou L, Yu JX, Wang H, Zhao D (2018) Answering natural language questions by subgraph matching over knowledge graphs. TKDE 30(5):824–837
Cai Q, Yates A (2013) Large-scale semantic parsing via schema matching and lexicon extension. In: ACL, pp 423–433
Krishnamurthy J, Mitchell TM (2012) Weakly supervised training of semantic parsers. In: EMNLP-CoNLL, pp 754–765
Bordes A, Weston J, Usunier N (2014b) Open question answering with weakly supervised embedding models. In: Proceedings of ECML-PKDD, pp 165–180
Hao Y, Zhang Y, Liu K, He S, Liu Z, Wu H, Zhao J (2017) An end-to-end model for question answering over knowledge base with cross-attention combining global knowledge. In: proceedings of the 55th annual meeting of the association for computational linguistics (vol. 1: Long Papers). Association for computational linguistics, pp 221–231
Yavuz S, Gur I, Su Y, Yan X (2017) Recovering question answering errors via query revision. In: proceedings of the 2017 conference on empirical methods in natural language processing. Association for Computational Linguistics, pp 903–909
Bordes A, Chopra S, Weston J (2014a) Question answering with subgraph embeddings. Empirical methods in natural language processing, pp 615–620
Zhou M, Huang M, Zhu X (2018) An interpretable reasoning network for Multi-Relation question answering. arXiv:1801.04726
Pasupat P, Liang P (2015) Compositional semantic parsing on semi-structured tables. Association for computational linguistics, pp 1470–1480
Yih WT, Richardson M, Meek C, Chang MW, Suh J (2016) The value of semantic parse labeling for knowledge base question answering. In: meeting of the association for computational linguistics, pp 201–206
Abujabal A, Roy RS, Yahya M, Weikum G (2017) Quint: Interpretable question answering over knowledge bases. In: proceedings of the 2017 conference on empirical methods in natural language processing: system demonstrations. Association for computational linguistics, pp 61–66
Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. Ann Conf Neural Inf Process Syst 4:3104–3112
Li D, Wei F, Zhou M, Xu K (2015) Question answering over freebase with multi-column convolutional neural networks. In: meeting of the association for computational linguistics and the international joint conference on natural language processing, pp 260–269
Weston J, Chopra S, Bordes A (2015) Memory networks. International conference on learning representations
Sukhbaatar S, Szlam A, Weston J, Fergus R (2015) End-to-end memory networks. Annual conference on neural information processing systems, pp 2440–2448
Kumar A, Irsoy O, Ondruska P, Iyyer M, Bradbury J, Gulrajani I, Socher Rx (2015) Ask me anything: dynamic memory networks for natural language processing. international conference on machine learning, pp 1378–1387
Shen Y, Huang P-S, Gao J, Chen W (2016) Reasonet: Learning to stop reading in machine comprehension. SIGKDD, pp 1047–1055
Wang W, Yang N, Wei F, Chang B, Zhou M (2017) Gated self-matching networks for reading comprehension and question answering. In: proceedings of the 55th annual meeting of the association for computational linguistics (vol. 1: Long Papers). Association for computational linguistics, pp 189– 198
Celikyilmaz A, Deng L, Li L, Wang C (2017) Scaffolding networks for teaching and learning to comprehend
Savenkov D, Agichtein E (2017) Evinets: Neural networks for combining evidence signals for factoid question answering. In: proceedings of the 55th annual meeting of the association for computational linguistics (vol. 2: Short Papers). Association for computational linguistics, pp 299– 304
Chen Y, Wu L, Zaki MJ (2019) Bidirectional attentive memory networks for question answering over knowledge bases. arXiv:1903.02188
Grefenstette E, Blunsom P, de Freitas N, Hermann MK (2014) Proceedings of the ACL 2014 workshop on semantic parsing, chapter a deep architecture for semantic parsing. Association for computational linguistics, pp 22–27
Iyyer M, Boyd-Graber J, Claudino L, Socher R, Daume III H (2014) A neural’ network for factoid question answering over paragraphs. In: proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP). Association for computational linguistics, pp 633–644
Yu L, Hermann KM, Blunsom P, Pulman S (2014) Deep learning for answer sentence selection. In: NIPS deep learning Workshop
Yih W-t, He X, Meek C (2014) Semantic parsing for single-relation question answering. Inproceedings of the 52nd annual meeting of the association for computational linguistics (Volume 2: Short Papers). Association for computational linguistics, pp 643–648
Fader A, Soderland S, Etzioni O (2011) Identifying relations for open information extraction. In: proceedings of the conference on empirical methods in natural language processing, EMNLP ’11, pp 1535–1545. Association for computational linguistics, stroudsburg
Liang C, Berant J, Le QV, Forbus KD, Ni Lao (2017) Neural symbolic machines: Learning semantic parsers on freebase with weak supervision. In: Proceedings of the 55th annual meeting of the association for computational linguistics, ACL 2017, vol 1. Long Papers, pp 23–33, Vancouver
Ansari GA, Saha A, Kumar V, Bhambhani M, Sankaranarayanan K, Chakrabarti S (2019) Neural program induction for KBQA without gold programs or query annotations. In: Proceedings of the twenty-eighth international joint conference on artificial Intelligence, IJCAI, Macao, vol 10-16, pp 4890– 4896
Yin P, Lu Z, Li H, Kao B (2015) Neural enquirer: Learning to query tables with natural language. Association for computational linguistics, pp 2308–2314
Mou L, Lu Z, Li H, Jin Z (2017) Coupling distributed and symbolic execution for natural language queries. In: proceedings of the 34th international conference on machine learning, Sydney, pp 2518–2526
Guu K, Miller J, Liang P (2015) Traversing knowledge graphs in vector space. Empirical methods in natural language processing, pp 318–327
Zhang L, Winn J, Tomioka R (2016) Gaussian attention model and its application to knowledge base embedding and question answering. CoRR, arXiv:1611.02266
Kingma D, Ba J (2015) Adam: A method for stochastic optimization. international conference on learning representations
Chen Z-Y, Chang C-H, Chen Y-P, Nayak J, Ku L-W (2019) Uhop: An unrestricted-hop relation extraction framework for knowledge-based question answering. inproceedings of the 2019 conference of the north american chapter of the association for computational linguistics: human language technologies, NAACLHLT 2019, vol 1. Long and Short Papers, Minneapolis, pp 345–356
Qin K, Wang Y, Li C, Gunaratna K, Jin H, Pavlu V et al (2020) A complex kbqa system using multiple reasoning paths
Saha A, Ansari GA, Laddha A, Chakrabarti S (2019) Complex program induction for querying knowledge bases in the absence of gold programs, pp 7185–200
Lan Y, Jiang J (2019) Knowledge base question answering with a matching-aggregation model and question-specific contextual Rel 27(10):1629–1638
Lan Y, Jiang J (2020) Query graph generation for answering multi-hop complex questions from knowledge bases. Proceedings of the 58th annual meeting of the association for computational linguistics
Acknowledgements
This work was supported in part by the National Social Science Foundation under Award 19BYY076, in part Key R & D project of Shandong Province 2019 JZZY010129, and in part by the Shandong Provincial Social Science Planning Project under Award 19BJCJ51, Award 18CXWJ01, and Award 18BJYJ04.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wu, W., Zhu, Z., Zhang, G. et al. A reasoning enhance network for muti-relation question answering. Appl Intell 51, 4515–4524 (2021). https://doi.org/10.1007/s10489-020-02111-6
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-020-02111-6