自然语言生成多表SQL查询语句技术研究

doi:10.3778/j.issn.1673-9418.1908025

摘要/Abstract

摘要：

自然语言生成SQL查询不仅是构建智能数据库查询系统的一个重要组成部分，亦是新型供电轨道交通系统混合时态大数据个性化运维的难点之一。目前利用深度学习模型的方法专注于数据库中单表SQL查询生成，无法解决数据库中多表SQL查询生成。针对这个问题，采用一种基于SQL语句模板填充的方法，将序列生成问题转化为多个分类问题，在训练深度学习模型的过程中充分利用SQL子句不同预测成分之间的依赖关系。在FROM子句的多表JOIN路径生成方面，将其建模为斯坦纳树问题，采用一种全局最优的算法来进行求解。在一个开放的文本生成SQL数据集Spider上对模型和算法进行实验验证，实验结果表明该方法能有效地提升多表SQL查询生成的查询匹配准确率。

关键词: 自然语言, SQL查询生成, 多表, 模板填充, 深度学习

Abstract:

SQL (structured query language) query generation from natural language is not only one of the most important parts of constructing intelligent database query system, but also one of the difficulties in the individualized operation and maintenance of hybrid temporal big data in the new power supply rail transit system. At present, the deep learning models almost focus on SQL query generation in a single table, but cannot solve multi-table SQL query generation in database. In order to solve this problem, this paper adopts a method named SQL sketch filling to transform the sequence generation problem into multiple classification problems. In the process of training the deep learning models, this paper makes full use of the dependencies of components in SQL clauses. In the generation of multi-table JOIN path of FROM clause, it is modeled as Steiner Tree problem and solved by a globally optimal algorithm. This method is validated on an open text-to-SQL dataset named Spider. The experimental results show that the model can improve the query-match accuracy of multi-table SQL query generation.

Key words: natural language, SQL (structured query language) query generation, multi-table, sketch filling, deep learning

曹金超，黄滔，陈刚，吴晓凡，陈珂. 自然语言生成多表SQL查询语句技术研究[J]. 计算机科学与探索, 2020, 14(7): 1133-1141.

CAO Jinchao, HUANG Tao, CHEN Gang, WU Xiaofan4, CHEN Ke. Research on Technology of Generating Multi-table SQL Query Statement by Natural Language[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(7): 1133-1141.

参考文献

[1] Baik C, Jagadish H V, Li Y Y. Bridging the semantic gap with SQL query logs in natural language interfaces to databases[J]. arXiv:1902.00031, 2019.
[2] Küpper D, Storbel M, R?sner D F. NAUDA: a cooperative natural language interface to relational databases[C]//Procee-dings of the 1993 ACM SIGMOD International Conference on Management of Data, Washington, May 26-28, 1993. New York: ACM, 1993: 529-533.
[3] Unger C, Bühmann L, Lehmann J, et al. Template-based question answering over RDF data[C]//Proceedings of the 21st World Wide Web Conference, Lyon, Apr 16-20, 2012. New York: ACM, 2012: 639-648.
[4] Li F, Jagadish H V. Constructing an interactive natural lang-uage interface for relational databases[J]. Proceedings of the VLDB Endowment, 2014, 8(1): 73-84.
[5] Bahdanau D, Cho K, Bengio Y, et al. Neural machine trans-lation by jointly learning to align and translate[C]//Proceed-ings of the 3rd International Conference on Learning Represen-tations, San Diego, May 7-9, 2015: 1-15.
[6] Li D, Lapata M. Language to logical form with neural atten-tion[C]//Proceedings of the 54th Annual Meeting of the Asso-ciation for Computational Linguistics, Berlin, Aug 7-12, 2016. Stroudsburg: ACL, 2016: 1-11.
[7] Wang C L, Brockschmidt M, Singh R. Pointing out SQL queries from text[J]. Microsoft Research: Artificial Intelli-gence, 2018.
[8] Xu X J, Liu C, Song D, et al. SQLNet: generating structured queries from natural language without reinforcement learn-ing[J]. arXiv:1711.04436, 2018.
[9] Devlin J, Chang M W, Lee K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[J]. arXiv:1810.04805, 2018.
[10] Liu X D, He P C, Chen W Z, et al. Multi-task deep neural networks for natural language understanding[J]. arXiv:1901. 11504, 2019.
[11] He P C, Mao Y, Chakrabarti K, et al. X-SQL: reinforce con-text into schema representation[J]. arXiv:1908.08113, 2019.
[12] Zhong V, Xiong C M, Socher R. Seq2SQL: generating struc-tured queries from natural language using reinforcement lear-ning[J]. arXiv:1709.00103, 2017.
[13] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[C]//Proceedings of the 2017 Annual Conference on Neural Information Processing Systems, Long Beach, Dec 4-9, 2017. Red Hook: Curran Associates, 2017: 6000-6010.
[14] Utama P, Weir N, Basik F, et al. An end-to-end neural natural language interface for databases[J]. arXiv:1804.00401, 2018.
[15] Kou L T, Markowsky G, Berman L, et al. A fast algorithm for Steiner trees[J]. Acta Informatica, 1981, 15(2): 141-145.
[16] Yu T, Zhang R, Yang K, et al. Spider: a large-scale human-labeled dataset for complex and cross-domain semantic parsing and text-to-SQL task[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Pro-cessing, Brussels, Oct 31-Nov 4, 2018. Stroudsburg: ACL, 2018: 3911-3921.
[17] Pennington J, Richard S, Manning C D. GloVe: global vec-tors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Oct 25-29, 2014. Stroudsburg: ACL, 2014: 1532-1543.
[18] Kingma D P, Ba J. Adam: a method for stochastic optimi-zation[C]//Proceedings of the 3rd International Conference on Learning Representations, San Diego, May 7-9, 2015: 1-15.