TY - GEN
T1 - Enhancing Text-to-SQL Parsing through Question Rewriting and Execution-Guided Refinement
AU - Mao, Wenxin
AU - Wang, Ruiqi
AU - Guo, Jiyu
AU - Zeng, Jichuan
AU - Gao, Cuiyun
AU - Han, Peiyi
AU - Liu, Chuanyi
N1 - Publisher Copyright:
© 2024 Association for Computational Linguistics.
PY - 2024
Y1 - 2024
N2 - 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 the execution accuracy (EX) metric.
AB - 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 the execution accuracy (EX) metric.
UR - https://www.scopus.com/pages/publications/85205322273
U2 - 10.18653/v1/2024.findings-acl.120
DO - 10.18653/v1/2024.findings-acl.120
M3 - 会议稿件
AN - SCOPUS:85205322273
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 2009
EP - 2024
BT - The 62nd Annual Meeting of the Association for Computational Linguistics
A2 - Ku, Lun-Wei
A2 - Martins, Andre
A2 - Srikumar, Vivek
PB - Association for Computational Linguistics (ACL)
T2 - Findings of the 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024
Y2 - 11 August 2024 through 16 August 2024
ER -