@inproceedings{radhakrishnan-etal-2020-colloql,
title = "{C}ollo{QL}: Robust Text-to-{SQL} Over Search Queries",
author = "Radhakrishnan, Karthik and
Srikantan, Arvind and
Lin, Xi Victoria",
editor = "Bogin, Ben and
Iyer, Srinivasan and
Lin, Xi Victoria and
Radev, Dragomir and
Suhr, Alane and
{Panupong} and
Xiong, Caiming and
Yin, Pengcheng and
Yu, Tao and
Zhang, Rui and
Zhong, Victor",
booktitle = "Proceedings of the First Workshop on Interactive and Executable Semantic Parsing",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.intexsempar-1.5",
doi = "10.18653/v1/2020.intexsempar-1.5",
pages = "34--45",
abstract = "Translating natural language utterances to executable queries is a helpful technique in making the vast amount of data stored in relational databases accessible to a wider range of non-tech-savvy end users. Prior work in this area has largely focused on textual input that is linguistically correct and semantically unambiguous. However, real-world user queries are often succinct, colloquial, and noisy, resembling the input of a search engine. In this work, we introduce data augmentation techniques and a sampling-based content-aware BERT model (ColloQL) to achieve robust text-to-SQL modeling over natural language search (NLS) questions. Due to the lack of evaluation data, we curate a new dataset of NLS questions and demonstrate the efficacy of our approach. ColloQL{'}s superior performance extends to well-formed text, achieving an 84.9{\%} (logical) and 90.7{\%} (execution) accuracy on the WikiSQL dataset, making it, to the best of our knowledge, the highest performing model that does not use execution guided decoding.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="radhakrishnan-etal-2020-colloql">
<titleInfo>
<title>ColloQL: Robust Text-to-SQL Over Search Queries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Karthik</namePart>
<namePart type="family">Radhakrishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arvind</namePart>
<namePart type="family">Srikantan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="given">Victoria</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Interactive and Executable Semantic Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Bogin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srinivasan</namePart>
<namePart type="family">Iyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="given">Victoria</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dragomir</namePart>
<namePart type="family">Radev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alane</namePart>
<namePart type="family">Suhr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name>
<namePart>Panupong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caiming</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengcheng</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victor</namePart>
<namePart type="family">Zhong</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>Translating natural language utterances to executable queries is a helpful technique in making the vast amount of data stored in relational databases accessible to a wider range of non-tech-savvy end users. Prior work in this area has largely focused on textual input that is linguistically correct and semantically unambiguous. However, real-world user queries are often succinct, colloquial, and noisy, resembling the input of a search engine. In this work, we introduce data augmentation techniques and a sampling-based content-aware BERT model (ColloQL) to achieve robust text-to-SQL modeling over natural language search (NLS) questions. Due to the lack of evaluation data, we curate a new dataset of NLS questions and demonstrate the efficacy of our approach. ColloQL’s superior performance extends to well-formed text, achieving an 84.9% (logical) and 90.7% (execution) accuracy on the WikiSQL dataset, making it, to the best of our knowledge, the highest performing model that does not use execution guided decoding.</abstract>
<identifier type="citekey">radhakrishnan-etal-2020-colloql</identifier>
<identifier type="doi">10.18653/v1/2020.intexsempar-1.5</identifier>
<location>
<url>https://aclanthology.org/2020.intexsempar-1.5</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>34</start>
<end>45</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ColloQL: Robust Text-to-SQL Over Search Queries
%A Radhakrishnan, Karthik
%A Srikantan, Arvind
%A Lin, Xi Victoria
%Y Bogin, Ben
%Y Iyer, Srinivasan
%Y Lin, Xi Victoria
%Y Radev, Dragomir
%Y Suhr, Alane
%Y Xiong, Caiming
%Y Yin, Pengcheng
%Y Yu, Tao
%Y Zhang, Rui
%Y Zhong, Victor
%E Panupong
%S Proceedings of the First Workshop on Interactive and Executable Semantic Parsing
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F radhakrishnan-etal-2020-colloql
%X Translating natural language utterances to executable queries is a helpful technique in making the vast amount of data stored in relational databases accessible to a wider range of non-tech-savvy end users. Prior work in this area has largely focused on textual input that is linguistically correct and semantically unambiguous. However, real-world user queries are often succinct, colloquial, and noisy, resembling the input of a search engine. In this work, we introduce data augmentation techniques and a sampling-based content-aware BERT model (ColloQL) to achieve robust text-to-SQL modeling over natural language search (NLS) questions. Due to the lack of evaluation data, we curate a new dataset of NLS questions and demonstrate the efficacy of our approach. ColloQL’s superior performance extends to well-formed text, achieving an 84.9% (logical) and 90.7% (execution) accuracy on the WikiSQL dataset, making it, to the best of our knowledge, the highest performing model that does not use execution guided decoding.
%R 10.18653/v1/2020.intexsempar-1.5
%U https://aclanthology.org/2020.intexsempar-1.5
%U https://doi.org/10.18653/v1/2020.intexsempar-1.5
%P 34-45
Markdown (Informal)
[ColloQL: Robust Text-to-SQL Over Search Queries](https://aclanthology.org/2020.intexsempar-1.5) (Radhakrishnan et al., intexsempar 2020)
ACL
- Karthik Radhakrishnan, Arvind Srikantan, and Xi Victoria Lin. 2020. ColloQL: Robust Text-to-SQL Over Search Queries. In Proceedings of the First Workshop on Interactive and Executable Semantic Parsing, pages 34–45, Online. Association for Computational Linguistics.