@inproceedings{guo-etal-2021-chase,
title = "Chase: A Large-Scale and Pragmatic {C}hinese Dataset for Cross-Database Context-Dependent Text-to-{SQL}",
author = "Guo, Jiaqi and
Si, Ziliang and
Wang, Yu and
Liu, Qian and
Fan, Ming and
Lou, Jian-Guang and
Yang, Zijiang and
Liu, Ting",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.180",
doi = "10.18653/v1/2021.acl-long.180",
pages = "2316--2331",
abstract = "The cross-database context-dependent Text-to-SQL (XDTS) problem has attracted considerable attention in recent years due to its wide range of potential applications. However, we identify two biases in existing datasets for XDTS: (1) a high proportion of context-independent questions and (2) a high proportion of easy SQL queries. These biases conceal the major challenges in XDTS to some extent. In this work, we present Chase, a large-scale and pragmatic Chinese dataset for XDTS. It consists of 5,459 coherent question sequences (17,940 questions with their SQL queries annotated) over 280 databases, in which only 35{\%} of questions are context-independent, and 28{\%} of SQL queries are easy. We experiment on Chase with three state-of-the-art XDTS approaches. The best approach only achieves an exact match accuracy of 40{\%} over all questions and 16{\%} over all question sequences, indicating that Chase highlights the challenging problems of XDTS. We believe that XDTS can provide fertile soil for addressing the problems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guo-etal-2021-chase">
<titleInfo>
<title>Chase: A Large-Scale and Pragmatic Chinese Dataset for Cross-Database Context-Dependent Text-to-SQL</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaqi</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziliang</namePart>
<namePart type="family">Si</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qian</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian-Guang</namePart>
<namePart type="family">Lou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zijiang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The cross-database context-dependent Text-to-SQL (XDTS) problem has attracted considerable attention in recent years due to its wide range of potential applications. However, we identify two biases in existing datasets for XDTS: (1) a high proportion of context-independent questions and (2) a high proportion of easy SQL queries. These biases conceal the major challenges in XDTS to some extent. In this work, we present Chase, a large-scale and pragmatic Chinese dataset for XDTS. It consists of 5,459 coherent question sequences (17,940 questions with their SQL queries annotated) over 280 databases, in which only 35% of questions are context-independent, and 28% of SQL queries are easy. We experiment on Chase with three state-of-the-art XDTS approaches. The best approach only achieves an exact match accuracy of 40% over all questions and 16% over all question sequences, indicating that Chase highlights the challenging problems of XDTS. We believe that XDTS can provide fertile soil for addressing the problems.</abstract>
<identifier type="citekey">guo-etal-2021-chase</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.180</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.180</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>2316</start>
<end>2331</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Chase: A Large-Scale and Pragmatic Chinese Dataset for Cross-Database Context-Dependent Text-to-SQL
%A Guo, Jiaqi
%A Si, Ziliang
%A Wang, Yu
%A Liu, Qian
%A Fan, Ming
%A Lou, Jian-Guang
%A Yang, Zijiang
%A Liu, Ting
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F guo-etal-2021-chase
%X The cross-database context-dependent Text-to-SQL (XDTS) problem has attracted considerable attention in recent years due to its wide range of potential applications. However, we identify two biases in existing datasets for XDTS: (1) a high proportion of context-independent questions and (2) a high proportion of easy SQL queries. These biases conceal the major challenges in XDTS to some extent. In this work, we present Chase, a large-scale and pragmatic Chinese dataset for XDTS. It consists of 5,459 coherent question sequences (17,940 questions with their SQL queries annotated) over 280 databases, in which only 35% of questions are context-independent, and 28% of SQL queries are easy. We experiment on Chase with three state-of-the-art XDTS approaches. The best approach only achieves an exact match accuracy of 40% over all questions and 16% over all question sequences, indicating that Chase highlights the challenging problems of XDTS. We believe that XDTS can provide fertile soil for addressing the problems.
%R 10.18653/v1/2021.acl-long.180
%U https://aclanthology.org/2021.acl-long.180
%U https://doi.org/10.18653/v1/2021.acl-long.180
%P 2316-2331
Markdown (Informal)
[Chase: A Large-Scale and Pragmatic Chinese Dataset for Cross-Database Context-Dependent Text-to-SQL](https://aclanthology.org/2021.acl-long.180) (Guo et al., ACL-IJCNLP 2021)
ACL