Abstract
Structured Query Language (SQL) is a query language widely used in databases, Text2SQL automatically parses natural language into SQL, which has great potential to facilitate non-expert users to query and mine structured data using natural language. Current research focuses on improving the matching accuracy of SQL clause tasks, but ignores the correctness of SQL syntax generation, and SQL generation involving multi-table joins still suffers from a large number of errors. Therefore, a neural network-based Text2SQL approach is proposed. To implement a practical Text2SQL workflow, the model associates natural language queries with an inverse normalized database schema, called INSL (Inverse Normalized Schema Link Generation Network). Through theoretical analysis and experimental validation on the public dataset Spider, INSL can effectively improve the quality of Text2SQL tasks.
Industry-University-Research Innovation Fund Project of Science and Technology Development Center of Ministry of Education (No. 2020QT08).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Choi D.H., Shin, M.C., Kim, E.G.: RYANSQL: recursively applying sketch-based slot fillings for complex text-to-SQL in cross-domain databases, pp. 309-332. CL (2021)
Zhen, D., Sun, S.Z., Liu, H.Z., Lou, J.G., et al.: Data-anonymous encoding for text-to-SQL generation. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 5405-5414. ACL, Hong Kong (2019)
Fu, X.Y., Shi, W.J., Yu, X.D., Zhao, Z., et al.: Design challenges in low-resource cross-lingual entity linking. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 6418-6432 (2020)
Rijhwani, S., Xie, J., Neubig, G., et al.: Zero-shot neural transfer for cross-lingual entity linking. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 6924-6931 (2019)
Logeswaran, L., Chang, M.W., Lee, K., et al.: Zero-shot entity linking by reading entity descriptions. http://arxiv.org/abs/1906.07348
Xu, P.Y., Hu, Q.: An end-to-end approach for handling unknown slot values in dialogue state tracking. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pp. 1448-1457. ACL, Australia (2018)
Nouri, E., Hosseini-Asl, E.: Toward scalable neural dialogue state tracking model. http://arxiv.org/abs/1812.00899
Herzig, J., Berant, J.: Decoupling structure and lexicon for zero-shot semantic parsing. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 1619-1629. ACL, Belgium (2018)
Guo, J., Zhan, Z., Gao, Y.: Towards complex text-to-SQL in cross-domain database with intermediate representation, pp. 4524-4535. ACL, Florence (2019)
Bogin, B., Berant, J., Gardner, M.: Representing schema structure with graph neural networks for text-to-SQL parsing. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, pp. 4560-4565. ACL, Florence (2019)
Wang, B.L., Shin, R., Liu, X.D., et al.: RAT-SQL: relation-aware schema encoding and linking for text-to-SQL parsers. In: Proceedings of the 58th Annual Meeting of the Association for Computational Association for Computational Linguistics, pp. 7567-7578. ACL (2020)
Zhong, V., Xiong, C., Socher, R.: Seq2SQL: generating structured queries from natural language using reinforcement learning. https://arxiv.org/abs/1709.00103
Acknowledgments
This work is supported and assisted by the Industry-University-Research Innovation Fund Project of Science and Technology Development Center of Ministry of Education (No. 2020QT08), National People’s Committee Training Program for Young and Middle-aged Talents (MZR20007), Hubei Science and Technology Major Special Project (2020AEA011), Wuhan Science and Technology Plan Applied Basic Frontier Project (2020020601012267).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Jun, T., Ziqi, F., Chong, S., Lu, Z., Boer, Z. (2023). INSL: Text2SQL Generation Based on Inverse Normalized Schema Linking. In: Liang, Q., Wang, W., Mu, J., Liu, X., Na, Z. (eds) Artificial Intelligence in China. AIC 2022. Lecture Notes in Electrical Engineering, vol 871. Springer, Singapore. https://doi.org/10.1007/978-981-99-1256-8_23
Download citation
DOI: https://doi.org/10.1007/978-981-99-1256-8_23
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1255-1
Online ISBN: 978-981-99-1256-8
eBook Packages: Computer ScienceComputer Science (R0)