@inproceedings{zhang-etal-2023-css,
title = "{CSS}: A Large-scale Cross-schema {C}hinese Text-to-{SQL} Medical Dataset",
author = "Zhang, Hanchong and
Li, Jieyu and
Chen, Lu and
Cao, Ruisheng and
Zhang, Yunyan and
Huang, Yu and
Zheng, Yefeng and
Yu, Kai",
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.435",
doi = "10.18653/v1/2023.findings-acl.435",
pages = "6970--6983",
abstract = "The cross-domain text-to-SQL task aims to build a system that can parse user questions into SQL on complete unseen databases, and the single-domain text-to-SQL task evaluates the performance on identical databases. Both of these setups confront unavoidable difficulties in real-world applications. To this end, we introduce the cross-schema text-to-SQL task, where the databases of evaluation data are different from that in the training data but come from the same domain. Furthermore, we present CSS, a large-scale CrosS-Schema Chinese text-to-SQL dataset, to carry on corresponding studies. CSS originally consisted of 4,340 question/SQL pairs across 2 databases. In order to generalize models to different medical systems, we extend CSS and create 19 new databases along with 29,280 corresponding dataset examples. Moreover, CSS is also a large corpus for single-domain Chinese text-to-SQL studies. We present the data collection approach and a series of analyses of the data statistics. To show the potential and usefulness of CSS, benchmarking baselines have been conducted and reported. Our dataset is publicly available at \url{https://huggingface.co/datasets/zhanghanchong/css}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2023-css">
<titleInfo>
<title>CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hanchong</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruisheng</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yefeng</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Yu</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>The cross-domain text-to-SQL task aims to build a system that can parse user questions into SQL on complete unseen databases, and the single-domain text-to-SQL task evaluates the performance on identical databases. Both of these setups confront unavoidable difficulties in real-world applications. To this end, we introduce the cross-schema text-to-SQL task, where the databases of evaluation data are different from that in the training data but come from the same domain. Furthermore, we present CSS, a large-scale CrosS-Schema Chinese text-to-SQL dataset, to carry on corresponding studies. CSS originally consisted of 4,340 question/SQL pairs across 2 databases. In order to generalize models to different medical systems, we extend CSS and create 19 new databases along with 29,280 corresponding dataset examples. Moreover, CSS is also a large corpus for single-domain Chinese text-to-SQL studies. We present the data collection approach and a series of analyses of the data statistics. To show the potential and usefulness of CSS, benchmarking baselines have been conducted and reported. Our dataset is publicly available at https://huggingface.co/datasets/zhanghanchong/css.</abstract>
<identifier type="citekey">zhang-etal-2023-css</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.435</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.435</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>6970</start>
<end>6983</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset
%A Zhang, Hanchong
%A Li, Jieyu
%A Chen, Lu
%A Cao, Ruisheng
%A Zhang, Yunyan
%A Huang, Yu
%A Zheng, Yefeng
%A Yu, Kai
%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 zhang-etal-2023-css
%X The cross-domain text-to-SQL task aims to build a system that can parse user questions into SQL on complete unseen databases, and the single-domain text-to-SQL task evaluates the performance on identical databases. Both of these setups confront unavoidable difficulties in real-world applications. To this end, we introduce the cross-schema text-to-SQL task, where the databases of evaluation data are different from that in the training data but come from the same domain. Furthermore, we present CSS, a large-scale CrosS-Schema Chinese text-to-SQL dataset, to carry on corresponding studies. CSS originally consisted of 4,340 question/SQL pairs across 2 databases. In order to generalize models to different medical systems, we extend CSS and create 19 new databases along with 29,280 corresponding dataset examples. Moreover, CSS is also a large corpus for single-domain Chinese text-to-SQL studies. We present the data collection approach and a series of analyses of the data statistics. To show the potential and usefulness of CSS, benchmarking baselines have been conducted and reported. Our dataset is publicly available at https://huggingface.co/datasets/zhanghanchong/css.
%R 10.18653/v1/2023.findings-acl.435
%U https://aclanthology.org/2023.findings-acl.435
%U https://doi.org/10.18653/v1/2023.findings-acl.435
%P 6970-6983
Markdown (Informal)
[CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset](https://aclanthology.org/2023.findings-acl.435) (Zhang et al., Findings 2023)
ACL
- Hanchong Zhang, Jieyu Li, Lu Chen, Ruisheng Cao, Yunyan Zhang, Yu Huang, Yefeng Zheng, and Kai Yu. 2023. CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset. In Findings of the Association for Computational Linguistics: ACL 2023, pages 6970–6983, Toronto, Canada. Association for Computational Linguistics.