Papers
Topics
Authors
Recent
Search
2000 character limit reached

Translating Natural Language Queries to SQL Using the T5 Model

Published 12 Dec 2023 in cs.DB, cs.AI, and cs.LG | (2312.12414v1)

Abstract: This paper presents the development process of a natural language to SQL model using the T5 model as the basis. The models, developed in August 2022 for an online transaction processing system and a data warehouse, have a 73\% and 84\% exact match accuracy respectively. These models, in conjunction with other work completed in the research project, were implemented for several companies and used successfully on a daily basis. The approach used in the model development could be implemented in a similar fashion for other database environments and with a more powerful pre-trained LLM.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. R. Rashed Mohassel, A. Fung, F. Mohammadi, and K. Raahemifar, “A survey on Advanced Metering Infrastructure,” International Journal of Electrical Power and Energy Systems, vol. 63, pp. 473–484, 2014.
  2. A. Wong, D. Joiner, C. Chiu, M. Elsayed, K. Pereira, Y. Khmelevsky, and J. Mahony, “A Survey of Natural Language Processing Implementation for Data Query Systems,” in RASSE 2021 - IEEE International Conference on Recent Advances in Systems Science and Engineering, Proceedings, 2021.
  3. K. Affolter, K. Stockinger, and A. Bernstein, “A comparative survey of recent natural language interfaces for databases,” VLDB Journal, vol. 28, no. 5, pp. 793–819, 10 2019.
  4. H. Li, J. Zhang, C. Li, and H. Chen, “RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL,” in Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI), 2 2023. [Online]. Available: http://arxiv.org/abs/2302.05965
  5. J. Li, B. Hui, R. Cheng, B. Qin, C. Ma, N. Huo, F. Huang, W. Du, L. Si, and Y. Li, “Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing,” 1 2023. [Online]. Available: http://arxiv.org/abs/2301.07507
  6. M. Pourreza and D. Rafiei, “DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction,” arXiv preprint arXiv:2304.11015, 4 2023. [Online]. Available: http://arxiv.org/abs/2304.11015
  7. D. Joiner, M. Clement, S. Chan, K. Pereira, A. Wong, Y. Khmelevsky, J. Mahony, and M. Ferri, “DW vs OLTP Performance Optimization in the Cloud on PostgreSQL (A Case Study),” in RASSE 2022 - IEEE International Conference on Recent Advances in Systems Science and Engineering, Symposium Proceedings, 2022.
  8. M. Uma, V. Sneha, G. Sneha, J. Bhuvana, and B. Bharathi, “Formation of SQL from Natural Language Queryusing NLP,” in 2019 International Conference on Computational Intelligence in Data Science (ICCIDS).   IEEE, 2019.
  9. N. Deng, Y. Chen, and Y. Zhang, “Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect,” arXiv preprint arXiv:2208.10099., 8 2022. [Online]. Available: http://arxiv.org/abs/2208.10099
  10. T. Yu, R. Zhang, K. Yang, M. Yasunaga, D. Wang, Z. Li, J. Ma, I. Li, Q. Yao, S. Roman, Z. Zhang, and D. Radev, “Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task,” arXiv preprint arXiv:1809.08887, 9 2018. [Online]. Available: http://arxiv.org/abs/1809.08887
  11. Q. Li, L. Li, Q. Li, and J. Zhong, “A Comprehensive Exploration on Spider with Fuzzy Decision Text-to-SQL Model,” IEEE Transactions on Industrial Informatics, vol. 16, no. 4, pp. 2542–2550, 4 2020.
  12. T. Guo and H. Gao, “Content Enhanced BERT-based Text-to-SQL Generation,” arXiv preprint arXiv:1910.07179, 10 2019. [Online]. Available: http://arxiv.org/abs/1910.07179
  13. V. Zhong, C. Xiong, and R. Socher, “Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning,” arXiv preprint arXiv:1709.00103., 8 2017. [Online]. Available: http://arxiv.org/abs/1709.00103
  14. Y. Mellah, E. H. Ettifouri, A. Rhouati, W. Dahhane, T. Bouchentouf, and M. G. Belkasmi, “SQL Generation from Natural Language Using Supervised Learning and Recurrent Neural Networks,” in Lecture Notes in Networks and Systems.   Springer, 2021, vol. 144, pp. 175–183.
  15. B. Bogin, M. Gardner, and J. Berant, “Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing,” arXiv preprint arXiv:1905.06241., 5 2019. [Online]. Available: http://arxiv.org/abs/1905.06241
  16. Z. Chen, L. Chen, Y. Zhao, R. Cao, Z. Xu, S. Zhu, and K. Yu, “ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser,” arXiv preprint arXiv:2104.04689, 4 2021. [Online]. Available: http://arxiv.org/abs/2104.04689
  17. B. Hui, R. Geng, L. Wang, B. Qin, B. Li, J. Sun, and Y. Li, “S2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers,” arXiv preprint arXiv:2203.06958., 3 2022. [Online]. Available: http://arxiv.org/abs/2203.06958
  18. R. Cai, J. Yuan, B. Xu, and Z. Hao, “SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL,” Neural Information Processing Systems, 34, 7664-7676., vol. 34, pp. 7664–7676, 10 2021. [Online]. Available: http://arxiv.org/abs/2111.00653
  19. B. Wang, R. Shin, X. Liu, O. Polozov, and M. Richardson, “RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers,” arXiv preprint arXiv:1911.04942, 11 2019. [Online]. Available: http://arxiv.org/abs/1911.04942
  20. J. Pennington, R. Socher, and C. D. Manning, “GloVe: Global Vectors for Word Representation,” in Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), 2014, pp. 1532–1543. [Online]. Available: http://nlp.
  21. S. Ferreira, G. Leitão, I. Silva, A. Martins, and P. Ferrari, “Evaluating human-machine translation with attention mechanisms for industry 4.0 environment SQL-based systems,” in IEEE International Workshop on Metrology for Industry 4.0 & IoT, 2020, pp. 229–234.
  22. H. Vathsala and S. Koolagudi, “NLP2SQL Using Semi-supervised Learning,” in Advanced Computing: 10th International Conference, IACC 2020, Panaji, Goa, India, December 5–6, 2020 , Revised Selected Papers, Part I 10.   Springer, 2021, pp. 288–299.
  23. X. Xu, C. Liu, and D. Song, “SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning,” arXiv preprint arXiv:1711.04436, 11 2017. [Online]. Available: http://arxiv.org/abs/1711.04436
  24. H. Wang, J. Li, H. Wu, E. Hovy, and Y. Sun, “Pre-Trained Language Models and Their Applications,” Engineering, 9 2022.
  25. U. Brunner and K. Stockinger, “ValueNet: A Natural Language-to-SQL System that Learns from Database Information,” in 2021 IEEE 37th International Conference on Data Engineering (ICDE, 2021, pp. 2177–2182. [Online]. Available: https://yale-lily.github.io/spider
  26. W. Hwang, J. Yim, S. Park, and M. Seo, “A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization,” arXiv preprint arXiv:1902.01069, 2 2019. [Online]. Available: http://arxiv.org/abs/1902.01069
  27. D. Choi, M. C. Shin, E. Kim, and D. R. Shin, “RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases,” Computational Linguistics, vol. 47, no. 2, pp. 309–332, 4 2020. [Online]. Available: http://arxiv.org/abs/2004.03125
  28. J. Guo, Z. Zhan, Y. Gao, Y. Xiao, J.-G. Lou, T. Liu, and D. Zhang, “Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation,” arXiv preprint arXiv:1905.08205, 5 2019. [Online]. Available: http://arxiv.org/abs/1905.08205
  29. R. Cao, L. Chen, Z. Chen, Y. Zhao, S. Zhu, and K. Yu, “LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations,” arXiv preprint arXiv:2106.01093., 6 2021. [Online]. Available: http://arxiv.org/abs/2106.01093
  30. Y. Elazar, N. Kassner, S. Ravfogel, A. Ravichander, E. Hovy, H. Schütze, S. Schütze, and Y. Goldberg, “Measuring and Improving Consistency in Pretrained Language Models,” Transactions of the Association for Computational Linguistics, vol. 9, pp. 1012–1031, 2021. [Online]. Available: https://doi.org/10.1162/tacl
  31. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” arXiv preprint arXiv:1810.04805., 10 2018. [Online]. Available: http://arxiv.org/abs/1810.04805
  32. R. Zhang, T. Yu, H. Y. Er, S. Shim, E. Xue, X. V. Lin, T. Shi, C. Xiong, R. Sovher, and D. Radev, “Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions,” arXiv preprint arXiv:1909.00786., 2019.
  33. J. Ma, Z. Yan, S. Pang, Y. Zhang, and J. Shen, “Mention Extraction and Linking for SQL Query Generation,” arXiv preprint arXiv:2012.10074, 12 2020. [Online]. Available: http://arxiv.org/abs/2012.10074http://dx.doi.org/10.18653/v1/2020.emnlp-main.563
  34. X. V. Lin, R. Socher, and C. Xiong, “Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing,” arXiv preprint arXiv:2012.12627, 12 2020. [Online]. Available: http://arxiv.org/abs/2012.12627
  35. P. Shaw, M.-W. Chang, P. Pasupat, and K. Toutanova, “Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?” arXiv preprint arXiv:2010.12725., 10 2020. [Online]. Available: http://arxiv.org/abs/2010.12725
  36. C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, Y. Zhou, W. Li, and P. J. Liu, “Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer,” The Journal of Machine Learning Research, vol. 21, no. 1, pp. 5485–5551, 10 2019. [Online]. Available: http://arxiv.org/abs/1910.10683
  37. T. Xie, C. H. Wu, P. Shi, R. Zhong, T. Scholak, M. Yasunaga, C.-S. Wu, M. Zhong, P. Yin, S. I. Wang, V. Zhong, B. Wang, C. Li, C. Boyle, A. Ni, Z. Yao, D. Radev, C. Xiong, L. Kong, R. Zhang, N. A. Smith, L. Zettlemoyer, and T. Yu, “UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models,” arXiv preprint arXiv:2201.05966, 1 2022. [Online]. Available: http://arxiv.org/abs/2201.05966
  38. T. Scholak, N. Schucher, and D. Bahdanau, “PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models,” arXiv preprint arXiv:2109.05093, 9 2021. [Online]. Available: http://arxiv.org/abs/2109.05093
  39. J. Qi, J. Tang, Z. He, X. Wan, Y. Cheng, C. Zhou, X. Wang, Q. Zhang, and Z. Lin, “RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL,” arXiv preprint arXiv:2205.06983., 5 2022. [Online]. Available: http://arxiv.org/abs/2205.06983
  40. Y. Zhao, J. Jiang, Y. Hu, W. Lan, H. Zhu, A. Chauhan, A. Li, L. Pan, J. Wang, C.-W. Hang, S. Zhang, M. Dong, J. Lilien, P. Ng, Z. Wang, V. Castelli, and B. Xiang, “Importance of Synthesizing High-quality Data for Text-to-SQL Parsing,” arXiv preprint arXiv:2212.08785, 12 2022. [Online]. Available: http://arxiv.org/abs/2212.08785
  41. L. Zeng, S. H. K. Parthasarathi, and D. Hakkani-Tur, “N-Best Hypotheses Reranking for Text-To-SQL Systems,” in IEEE Spoken Language Technology Workshop (SLT), 10 2022, pp. 663–670. [Online]. Available: http://arxiv.org/abs/2210.10668
  42. Q. Liu, Z. Ye, T. Yu, P. Blunsom, and L. Song, “Augmenting Multi-Turn Text-to-SQL Datasets with Self-Play,” arXiv preprint arXiv:2210.12096, 10 2022. [Online]. Available: http://arxiv.org/abs/2210.12096
  43. A. Liu, X. Hu, L. Wen, and P. S. Yu, “A comprehensive evaluation of ChatGPT’s zero-shot Text-to-SQL capability,” arXiv preprint arXiv:2303.13547., 3 2023. [Online]. Available: http://arxiv.org/abs/2303.13547

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up