Text-to-SQL Error Correction with Language Models of Code

Ziru Chen, Shijie Chen, Michael White, Raymond Mooney, Ali Payani, Jayanth Srinivasa, Yu Su, Huan Sun


Abstract
Despite recent progress in text-to-SQL parsing, current semantic parsers are still not accurate enough for practical use. In this paper, we investigate how to build automatic text-to-SQL error correction models. Noticing that token-level edits are out of context and sometimes ambiguous, we propose building clause-level edit models instead. Besides, while most language models of code are not specifically pre-trained for SQL, they know common data structures and their operations in programming languages such as Python. Thus, we propose a novel representation for SQL queries and their edits that adheres more closely to the pre-training corpora of language models of code. Our error correction model improves the exact set match accuracy of different parsers by 2.4-6.5 and obtains up to 4.3 point absolute improvement over two strong baselines.
Anthology ID:
2023.acl-short.117
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1359–1372
Language:
URL:
https://aclanthology.org/2023.acl-short.117
DOI:
10.18653/v1/2023.acl-short.117
Bibkey:
Cite (ACL):
Ziru Chen, Shijie Chen, Michael White, Raymond Mooney, Ali Payani, Jayanth Srinivasa, Yu Su, and Huan Sun. 2023. Text-to-SQL Error Correction with Language Models of Code. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 1359–1372, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Text-to-SQL Error Correction with Language Models of Code (Chen et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-short.117.pdf
Video:
 https://aclanthology.org/2023.acl-short.117.mp4