Abstract
Question answering over knowledge graph (KGQA), which automatically answers natural language questions by querying the facts in knowledge graph (KG), has drawn significant attention in recent years. In this paper, we focus on single-relation questions, which can be answered through a single fact in KG. This task is a non-trivial problem since capturing the meaning of questions and selecting the golden fact from billions of facts in KG are both challengeable. We propose a pipeline framework for KGQA, which consists of three cascaded components: (1) an entity detection model, which can label the entity mention in the question; (2) a novel entity linking model, which considers the contextual information of candidate entities in KG and builds a question pattern classifier according to the correlations between question patterns and relation types to mitigate entity ambiguity problem; and (3) a simple yet effective relation detection model, which is used to match the semantic similarity between the question and relation candidates. Substantial experiments on the SimpleQuestions benchmark dataset show that our proposed method could achieve better performance than many existing state-of-the-art methods on accuracy, top-N recall and other evaluation metrics.
Similar content being viewed by others
References
Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. In: ‘ICLR’, OpenReview.net
Bao J, Duan N, Yan Z, Zhou M, Zhao T (2016) Constraint-based question answering with knowledge graph. In: ‘COLING’, ACL 2503–2514
Bhutani N, Zheng X, Qian K, Li Y, Jagadish H (2020) Answering complex questions by combining information from curated and extracted knowledge bases. In: ‘ACL’. The association for computer linguistics 1–10
Bollacker K, Evans C, Paritosh P, Sturge T, Taylor J (2008) Freebase: a collaboratively created graph database for structuring human knowledge. In: ‘SIGMOD’. ACM 1247–1250
Bordes A, Usunier N, Chopra S, Weston J (2015) ‘Large-scale simple question answering with memory networks. arXiv:1506.02075
Buzaaba H, Amagasa T (2019) A modular approach for efficient simple question answering over knowledge base. In: ‘DEXA’. Springer 237–246
Buzaaba H, Amagasa T (2021) Question answering over knowledge base: a scheme for integrating subject and the identified relation to answer simple questions. SN Comput Sci 2(1):25
Carlson A, Betteridge J, Kisiel B, Settles B, Hruschka E, Mitchell T (2010) Toward an architecture for never-ending language learning. In: ‘AAAI’, vol 24. AAAI Press
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. In: ‘NAACL’. Association for computational linguistics 345–356
Dai Z, Li L, Xu W (2016) CFO: conditional focused neural question answering with large-scale knowledge bases. In: ‘ACL’. The Association for Computer Linguistics
Dubey M, Banerjee D, Abdelkawi A, Lehmann J (2019) Lc-quad 2.0: a large dataset for complex question answering over wikidata and dbpedia. In: ‘ISWC’, Vol. 11779, Springer, pp 69–78
Han J, Cheng B, Wang X (2020) Two-phase hypergraph based reasoning with dynamic relations for multi-hop KBQA. In: ‘IJCAI’. IJCAI/AAAI Press 3615–3621
Hao Y, Liu H, He S, Liu K, Zhao J (2018) Pattern-revising enhanced simple question answering over knowledge bases. In: ‘COLING’. ACL 3272–3282
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: ‘ACL’. The Association for computer linguistics 221–231
He H, Singh AK (2008) Graphs-at-a-time: query language and access methods for graph databases. In: ‘SIGMOD’. ACM 405–418
He X, Golub D (2016) Character-level question answering with attention. In: ‘EMNLP’. The Association for computer linguistics 1598–1607
Herzig J, Berant J (2018) Decoupling structure and lexicon for zero-shot semantic parsing. In: ‘EMNLP’. Association for Computational Linguistics 1619–1629
Hu S, Zou L, Yu JX, Wang H, Zhao D (2018) Answering natural language questions by subgraph matching over knowledge graphs. IEEE Trans Knowl Data Eng 30(5):824–837
Huang X, Zhang J, Li D, Li P (2019) Knowledge graph embedding based question answering. In: ‘WSDM’. ACM 105–113
Kim Y (2014) Convolutional neural networks for sentence classification. In: ‘EMNLP’. The Association for computer linguistics 1746–1751
Lai S, Xu L, Liu K, Zhao J (2015) Recurrent convolutional neural networks for text classification. In: ‘AAAI’. AAAI Press 2267–2273
Lan Y, Jiang J (2020) Query graph generation for answering multi-hop complex questions from knowledge bases. In: ‘ACL’. The Association for Computer Linguistics 969–974
Lan Y, Wang S, Jiang J (2019a) 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
Lan Y, Wang S, Jiang J (2019b) Knowledge base question answering with topic units. In: ‘IJCAI’. IJCAI/AAAI Press 5046–5052
Lehmann J, Isele R, Jakob M, Jentzsch A, Kontokostas D, Mendes PN, Hellmann S, Morsey M, Van Kleef P, Auer S et al (2015) Dbpedia-a large-scale, multilingual knowledge base extracted from wikipedia. Semantic web 6(2):167–195
Liu P, Qiu X, Huang X (2016) Recurrent neural network for text classification with multi-task learning. In: ‘IJCAI’. IJCAI/AAAI Press 2873–2879
Lukovnikov D, Fischer A, Lehmann J (2019) Pretrained transformers for simple question answering over knowledge graphs. In: ‘ISWC’, Vol. 11778, Springer, pp 470–486
Lukovnikov D, Fischer A, Lehmann J, Auer S (2017) Neural network-based question answering over knowledge graphs on word and character level In: ‘WWW’. ACM 1211–1220
Mohammed S, Shi P, Lin J (2018) Strong baselines for simple question answering over knowledge graphs with and without neural networks. In: ‘NAACL’. The Association for Computer Linguistics 291–296
Petrochuk M, Zettlemoyer L (2018) Simplequestions nearly solved: a new upperbound and baseline approach. In: ‘EMNLP’. The Association for Computer Linguistics 554–558
Qu Y, Liu J, Kang L, Shi Q, Ye D (2018) ‘Question answering over freebase via attentive RNN with similarity matrix based CNN’. arXiv:1804.03317
Shen T, Geng X, Qin T, Guo D, Tang D, Duan N, Long G, Jiang D (2019) Multi-task learning for conversational question answering over a large-scale knowledge base. In: ‘EMNLP’. Association for Computational Linguistics 2442–2451
Su Y, Sun H, Sadler BM, Srivatsa M, Gur I, Yan Z, Yan X (2016) On generating characteristic-rich question sets for QA evaluation. In: ‘EMNLP’. The Association for Computer Linguistics 562–572
Suchanek FM, Kasneci G, Weikum G (2007) Yago: a core of semantic knowledge. In: ‘WWW’. ACM 697–706
Sun Y, Zhang L, Cheng G, Qu Y (2020) SPARQA: skeleton-based semantic parsing for complex questions over knowledge bases. In: ‘AAAI’. AAAI Press 8952–8959
Trivedi, P., Maheshwari, G., Dubey, M. and Lehmann, J. ( 2017) , Lc-quad: A corpus for complex question answering over knowledge graphs, in ‘ISWC’, Vol. 10588, Springer, pp. 210–218
Wang M, Liu J, Wei B, Yao S, Zeng H, Shi L (2019) Answering why-not questions on SPARQL queries. Knowl Inf Syst 58(1):169–208
Wang Y, Zhang R, Xu C, Mao Y (2018) The APVA-TURBO approach to question answering in knowledge base. In: ‘COLING’. ACL 1998–2009
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’. The Association for Computer Linguistics 1321–1331
Yin W, Yu M, Xiang B, Zhou B, Schütze H (2016) Simple question answering by attentive convolutional neural network. In: ‘COLING’. ACL 1746–1756
Zhang Y, Dai H, Kozareva Z, Smola AJ, Song L (2018) Variational reasoning for question answering with knowledge graph. In: ‘AAAI’. AAAI Press 6069–6076
Zhao W, Chung T, Goyal AK, Metallinou A (2019) Simple question answering with subgraph ranking and joint-scoring. In: ‘NAACL-HLT’. The Association for Computer Linguistics 324–334
Zheng W, Yu JX, Zou L, Cheng H (2018) Question answering over knowledge graphs: question understanding via template decomposition. Proc VLDB Endow 11(11):1373–1386
Zhou G, Xie Z, Yu Z, Huang JX (2021) DFM: a parameter-shared deep fused model for knowledge base question answering. Inf Sci 547:103–118
Acknowledgements
This work was supported by the National Natural Science Foundation of China under Grant Nos. 61872163 and 61806084 and Jilin Provincial Education Department project under Grant No. JJKH20190160KJ.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Hai Cui and Tao Peng: These authors contributed equally to this study and share first authorship.
Rights and permissions
About this article
Cite this article
Cui, H., Peng, T., Feng, L. et al. Simple Question Answering over Knowledge Graph Enhanced by Question Pattern Classification. Knowl Inf Syst 63, 2741–2761 (2021). https://doi.org/10.1007/s10115-021-01609-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10115-021-01609-w