Enhancing Text-to-SQL Parsing through Question Rewriting and Execution-Guided Refinement

Wenxin Mao, Ruiqi Wang, Jiyu Guo, Jichuan Zeng, Cuiyun Gao, Peiyi Han, Chuanyi Liu


Abstract
Large Language Model (LLM)-based approach has become the mainstream for Text-to-SQL task and achieves remarkable performance. In this paper, we augment the existing prompt engineering methods by exploiting the database content and execution feedback. Specifically, we introduce DART-SQL, which comprises two key components: (1) Question Rewriting: DART-SQL rewrites natural language questions by leveraging database content information to eliminate ambiguity. (2) Execution-Guided Refinement: DART-SQL incorporates database content information and utilizes the execution results of the generated SQL to iteratively refine the SQL. We apply this framework to the two LLM-based approaches (DAIL-SQL and C3) and test it on four widely used benchmarks (Spider-dev, Spider-test, Realistic and DK). Experiments show that our framework for DAIL-SQL and C3 achieves an average improvement of 12.41% and 5.38%, respectively, in terms of execution accuracy(EX) metric.
Anthology ID:
2024.findings-acl.120
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2009–2024
Language:
URL:
https://aclanthology.org/2024.findings-acl.120
DOI:
10.18653/v1/2024.findings-acl.120
Bibkey:
Cite (ACL):
Wenxin Mao, Ruiqi Wang, Jiyu Guo, Jichuan Zeng, Cuiyun Gao, Peiyi Han, and Chuanyi Liu. 2024. Enhancing Text-to-SQL Parsing through Question Rewriting and Execution-Guided Refinement. In Findings of the Association for Computational Linguistics: ACL 2024, pages 2009–2024, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Enhancing Text-to-SQL Parsing through Question Rewriting and Execution-Guided Refinement (Mao et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.120.pdf