@inproceedings{mao-etal-2024-enhancing,
title = "Enhancing Text-to-{SQL} Parsing through Question Rewriting and Execution-Guided Refinement",
author = "Mao, Wenxin and
Wang, Ruiqi and
Guo, Jiyu and
Zeng, Jichuan and
Gao, Cuiyun and
Han, Peiyi and
Liu, Chuanyi",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.120",
doi = "10.18653/v1/2024.findings-acl.120",
pages = "2009--2024",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mao-etal-2024-enhancing">
<titleInfo>
<title>Enhancing Text-to-SQL Parsing through Question Rewriting and Execution-Guided Refinement</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenxin</namePart>
<namePart type="family">Mao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruiqi</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiyu</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jichuan</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cuiyun</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peiyi</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuanyi</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">mao-etal-2024-enhancing</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.120</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.120</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>2009</start>
<end>2024</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Text-to-SQL Parsing through Question Rewriting and Execution-Guided Refinement
%A Mao, Wenxin
%A Wang, Ruiqi
%A Guo, Jiyu
%A Zeng, Jichuan
%A Gao, Cuiyun
%A Han, Peiyi
%A Liu, Chuanyi
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F mao-etal-2024-enhancing
%X 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.
%R 10.18653/v1/2024.findings-acl.120
%U https://aclanthology.org/2024.findings-acl.120
%U https://doi.org/10.18653/v1/2024.findings-acl.120
%P 2009-2024
Markdown (Informal)
[Enhancing Text-to-SQL Parsing through Question Rewriting and Execution-Guided Refinement](https://aclanthology.org/2024.findings-acl.120) (Mao et al., Findings 2024)
ACL