@inproceedings{hu-etal-2023-importance,
title = "Importance of Synthesizing High-quality Data for Text-to-{SQL} Parsing",
author = "Hu, Yiqun and
Zhao, Yiyun and
Jiang, Jiarong and
Lan, Wuwei and
Zhu, Henghui and
Chauhan, Anuj and
Li, Alexander Hanbo and
Pan, Lin and
Wang, Jun and
Hang, Chung-Wei and
Zhang, Sheng and
Guo, Jiang and
Dong, Mingwen and
Lilien, Joseph and
Ng, Patrick and
Wang, Zhiguo and
Castelli, Vittorio and
Xiang, Bing",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.86",
doi = "10.18653/v1/2023.findings-acl.86",
pages = "1327--1343",
abstract = "There has been increasing interest in synthesizing data to improve downstream text-to-SQL tasks. In this paper, we examined the existing synthesized datasets and discovered that state-of-the-art text-to-SQL algorithms did not further improve on popular benchmarks when trained with augmented synthetic data. We observed three shortcomings: illogical synthetic SQL queries from independent column sampling, arbitrary table joins, and language gaps between the synthesized SQL and natural language question (NLQ) pair. To address these issues, we propose a novel synthesis framework that imposes strong typing constraints, incorporates key relationships from schema, and conducts schema-distance-weighted column sampling. We also adopt an intermediate representation (IR) for the SQL-to-text task to further improve the quality of the generated NLQ. When existing powerful text-to-SQL parsers are pretrained on our high-quality synthesized data, these models have significant accuracy boosts and achieve new state-of-the-art performance on Spider. We also demonstrate the effectiveness of our techniques with ablation studies",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2023-importance">
<titleInfo>
<title>Importance of Synthesizing High-quality Data for Text-to-SQL Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yiqun</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiyun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiarong</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wuwei</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henghui</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anuj</namePart>
<namePart type="family">Chauhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="given">Hanbo</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Wei</namePart>
<namePart type="family">Hang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sheng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiang</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingwen</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Lilien</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiguo</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vittorio</namePart>
<namePart type="family">Castelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Xiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>There has been increasing interest in synthesizing data to improve downstream text-to-SQL tasks. In this paper, we examined the existing synthesized datasets and discovered that state-of-the-art text-to-SQL algorithms did not further improve on popular benchmarks when trained with augmented synthetic data. We observed three shortcomings: illogical synthetic SQL queries from independent column sampling, arbitrary table joins, and language gaps between the synthesized SQL and natural language question (NLQ) pair. To address these issues, we propose a novel synthesis framework that imposes strong typing constraints, incorporates key relationships from schema, and conducts schema-distance-weighted column sampling. We also adopt an intermediate representation (IR) for the SQL-to-text task to further improve the quality of the generated NLQ. When existing powerful text-to-SQL parsers are pretrained on our high-quality synthesized data, these models have significant accuracy boosts and achieve new state-of-the-art performance on Spider. We also demonstrate the effectiveness of our techniques with ablation studies</abstract>
<identifier type="citekey">hu-etal-2023-importance</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.86</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.86</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>1327</start>
<end>1343</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Importance of Synthesizing High-quality Data for Text-to-SQL Parsing
%A Hu, Yiqun
%A Zhao, Yiyun
%A Jiang, Jiarong
%A Lan, Wuwei
%A Zhu, Henghui
%A Chauhan, Anuj
%A Li, Alexander Hanbo
%A Pan, Lin
%A Wang, Jun
%A Hang, Chung-Wei
%A Zhang, Sheng
%A Guo, Jiang
%A Dong, Mingwen
%A Lilien, Joseph
%A Ng, Patrick
%A Wang, Zhiguo
%A Castelli, Vittorio
%A Xiang, Bing
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F hu-etal-2023-importance
%X There has been increasing interest in synthesizing data to improve downstream text-to-SQL tasks. In this paper, we examined the existing synthesized datasets and discovered that state-of-the-art text-to-SQL algorithms did not further improve on popular benchmarks when trained with augmented synthetic data. We observed three shortcomings: illogical synthetic SQL queries from independent column sampling, arbitrary table joins, and language gaps between the synthesized SQL and natural language question (NLQ) pair. To address these issues, we propose a novel synthesis framework that imposes strong typing constraints, incorporates key relationships from schema, and conducts schema-distance-weighted column sampling. We also adopt an intermediate representation (IR) for the SQL-to-text task to further improve the quality of the generated NLQ. When existing powerful text-to-SQL parsers are pretrained on our high-quality synthesized data, these models have significant accuracy boosts and achieve new state-of-the-art performance on Spider. We also demonstrate the effectiveness of our techniques with ablation studies
%R 10.18653/v1/2023.findings-acl.86
%U https://aclanthology.org/2023.findings-acl.86
%U https://doi.org/10.18653/v1/2023.findings-acl.86
%P 1327-1343
Markdown (Informal)
[Importance of Synthesizing High-quality Data for Text-to-SQL Parsing](https://aclanthology.org/2023.findings-acl.86) (Hu et al., Findings 2023)
ACL
- Yiqun Hu, Yiyun Zhao, Jiarong Jiang, Wuwei Lan, Henghui Zhu, Anuj Chauhan, Alexander Hanbo Li, Lin Pan, Jun Wang, Chung-Wei Hang, Sheng Zhang, Jiang Guo, Mingwen Dong, Joseph Lilien, Patrick Ng, Zhiguo Wang, Vittorio Castelli, and Bing Xiang. 2023. Importance of Synthesizing High-quality Data for Text-to-SQL Parsing. In Findings of the Association for Computational Linguistics: ACL 2023, pages 1327–1343, Toronto, Canada. Association for Computational Linguistics.