@inproceedings{chen-etal-2019-nl2psql,
title = "{NL}2p{SQL}: Generating Pseudo-{SQL} Queries from Under-Specified Natural Language Questions",
author = "Chen, Fuxiang and
Hwang, Seung-won and
Choo, Jaegul and
Ha, Jung-Woo and
Kim, Sunghun",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1262",
doi = "10.18653/v1/D19-1262",
pages = "2603--2613",
abstract = "Generating SQL codes from natural language questions (NL2SQL) is an emerging research area. Existing studies have mainly focused on clear scenarios where specified information is fully given to generate a SQL query. However, in developer forums such as Stack Overflow, questions cover more diverse tasks including table manipulation or performance issues, where a table is not specified. The SQL query posted in Stack Overflow, Pseudo-SQL (pSQL), does not usually contain table schemas and is not necessarily executable, is sufficient to guide developers. Here we describe a new NL2pSQL task to generate pSQL codes from natural language questions on under-specified database issues, NL2pSQL. In addition, we define two new metrics suitable for the proposed NL2pSQL task, Canonical-BLEU and SQL-BLEU, instead of the conventional BLEU. With a baseline model using sequence-to-sequence architecture integrated by denoising autoencoder, we confirm the validity of our task. Experiments show that the proposed NL2pSQL approach yields well-formed queries (up to 43{\%} more than a standard Seq2Seq model). Our code and datasets will be publicly released.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2019-nl2psql">
<titleInfo>
<title>NL2pSQL: Generating Pseudo-SQL Queries from Under-Specified Natural Language Questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fuxiang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seung-won</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaegul</namePart>
<namePart type="family">Choo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jung-Woo</namePart>
<namePart type="family">Ha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunghun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Generating SQL codes from natural language questions (NL2SQL) is an emerging research area. Existing studies have mainly focused on clear scenarios where specified information is fully given to generate a SQL query. However, in developer forums such as Stack Overflow, questions cover more diverse tasks including table manipulation or performance issues, where a table is not specified. The SQL query posted in Stack Overflow, Pseudo-SQL (pSQL), does not usually contain table schemas and is not necessarily executable, is sufficient to guide developers. Here we describe a new NL2pSQL task to generate pSQL codes from natural language questions on under-specified database issues, NL2pSQL. In addition, we define two new metrics suitable for the proposed NL2pSQL task, Canonical-BLEU and SQL-BLEU, instead of the conventional BLEU. With a baseline model using sequence-to-sequence architecture integrated by denoising autoencoder, we confirm the validity of our task. Experiments show that the proposed NL2pSQL approach yields well-formed queries (up to 43% more than a standard Seq2Seq model). Our code and datasets will be publicly released.</abstract>
<identifier type="citekey">chen-etal-2019-nl2psql</identifier>
<identifier type="doi">10.18653/v1/D19-1262</identifier>
<location>
<url>https://aclanthology.org/D19-1262</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>2603</start>
<end>2613</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NL2pSQL: Generating Pseudo-SQL Queries from Under-Specified Natural Language Questions
%A Chen, Fuxiang
%A Hwang, Seung-won
%A Choo, Jaegul
%A Ha, Jung-Woo
%A Kim, Sunghun
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F chen-etal-2019-nl2psql
%X Generating SQL codes from natural language questions (NL2SQL) is an emerging research area. Existing studies have mainly focused on clear scenarios where specified information is fully given to generate a SQL query. However, in developer forums such as Stack Overflow, questions cover more diverse tasks including table manipulation or performance issues, where a table is not specified. The SQL query posted in Stack Overflow, Pseudo-SQL (pSQL), does not usually contain table schemas and is not necessarily executable, is sufficient to guide developers. Here we describe a new NL2pSQL task to generate pSQL codes from natural language questions on under-specified database issues, NL2pSQL. In addition, we define two new metrics suitable for the proposed NL2pSQL task, Canonical-BLEU and SQL-BLEU, instead of the conventional BLEU. With a baseline model using sequence-to-sequence architecture integrated by denoising autoencoder, we confirm the validity of our task. Experiments show that the proposed NL2pSQL approach yields well-formed queries (up to 43% more than a standard Seq2Seq model). Our code and datasets will be publicly released.
%R 10.18653/v1/D19-1262
%U https://aclanthology.org/D19-1262
%U https://doi.org/10.18653/v1/D19-1262
%P 2603-2613
Markdown (Informal)
[NL2pSQL: Generating Pseudo-SQL Queries from Under-Specified Natural Language Questions](https://aclanthology.org/D19-1262) (Chen et al., EMNLP-IJCNLP 2019)
ACL