@inproceedings{hazoom-etal-2021-text,
title = "Text-to-{SQL} in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data",
author = "Hazoom, Moshe and
Malik, Vibhor and
Bogin, Ben",
editor = "Lachmy, Royi and
Yao, Ziyu and
Durrett, Greg and
Gligoric, Milos and
Li, Junyi Jessy and
Mooney, Ray and
Neubig, Graham and
Su, Yu and
Sun, Huan and
Tsarfaty, Reut",
booktitle = "Proceedings of the 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.nlp4prog-1.9/",
doi = "10.18653/v1/2021.nlp4prog-1.9",
pages = "77--87",
abstract = "Most available semantic parsing datasets, comprising of pairs of natural utterances and logical forms, were collected solely for the purpose of training and evaluation of natural language understanding systems. As a result, they do not contain any of the richness and variety of natural-occurring utterances, where humans ask about data they need or are curious about. In this work, we release SEDE, a dataset with 12,023 pairs of utterances and SQL queries collected from real usage on the Stack Exchange website. We show that these pairs contain a variety of real-world challenges which were rarely reflected so far in any other semantic parsing dataset, propose an evaluation metric based on comparison of partial query clauses that is more suitable for real-world queries, and conduct experiments with strong baselines, showing a large gap between the performance on SEDE compared to other common datasets."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hazoom-etal-2021-text">
<titleInfo>
<title>Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Moshe</namePart>
<namePart type="family">Hazoom</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vibhor</namePart>
<namePart type="family">Malik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Bogin</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 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Royi</namePart>
<namePart type="family">Lachmy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziyu</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Durrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Milos</namePart>
<namePart type="family">Gligoric</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junyi</namePart>
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ray</namePart>
<namePart type="family">Mooney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reut</namePart>
<namePart type="family">Tsarfaty</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>Most available semantic parsing datasets, comprising of pairs of natural utterances and logical forms, were collected solely for the purpose of training and evaluation of natural language understanding systems. As a result, they do not contain any of the richness and variety of natural-occurring utterances, where humans ask about data they need or are curious about. In this work, we release SEDE, a dataset with 12,023 pairs of utterances and SQL queries collected from real usage on the Stack Exchange website. We show that these pairs contain a variety of real-world challenges which were rarely reflected so far in any other semantic parsing dataset, propose an evaluation metric based on comparison of partial query clauses that is more suitable for real-world queries, and conduct experiments with strong baselines, showing a large gap between the performance on SEDE compared to other common datasets.</abstract>
<identifier type="citekey">hazoom-etal-2021-text</identifier>
<identifier type="doi">10.18653/v1/2021.nlp4prog-1.9</identifier>
<location>
<url>https://aclanthology.org/2021.nlp4prog-1.9/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>77</start>
<end>87</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data
%A Hazoom, Moshe
%A Malik, Vibhor
%A Bogin, Ben
%Y Lachmy, Royi
%Y Yao, Ziyu
%Y Durrett, Greg
%Y Gligoric, Milos
%Y Li, Junyi Jessy
%Y Mooney, Ray
%Y Neubig, Graham
%Y Su, Yu
%Y Sun, Huan
%Y Tsarfaty, Reut
%S Proceedings of the 1st Workshop on Natural Language Processing for Programming (NLP4Prog 2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F hazoom-etal-2021-text
%X Most available semantic parsing datasets, comprising of pairs of natural utterances and logical forms, were collected solely for the purpose of training and evaluation of natural language understanding systems. As a result, they do not contain any of the richness and variety of natural-occurring utterances, where humans ask about data they need or are curious about. In this work, we release SEDE, a dataset with 12,023 pairs of utterances and SQL queries collected from real usage on the Stack Exchange website. We show that these pairs contain a variety of real-world challenges which were rarely reflected so far in any other semantic parsing dataset, propose an evaluation metric based on comparison of partial query clauses that is more suitable for real-world queries, and conduct experiments with strong baselines, showing a large gap between the performance on SEDE compared to other common datasets.
%R 10.18653/v1/2021.nlp4prog-1.9
%U https://aclanthology.org/2021.nlp4prog-1.9/
%U https://doi.org/10.18653/v1/2021.nlp4prog-1.9
%P 77-87
Markdown (Informal)
[Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange Data](https://aclanthology.org/2021.nlp4prog-1.9/) (Hazoom et al., NLP4Prog 2021)
ACL