@inproceedings{giaquinto-etal-2023-multitask,
title = "Multitask Pretraining with Structured Knowledge for Text-to-{SQL} Generation",
author = "Giaquinto, Robert and
Zhang, Dejiao and
Kleiner, Benjamin and
Li, Yang and
Tan, Ming and
Bhatia, Parminder and
Nallapati, Ramesh and
Ma, Xiaofei",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.620",
doi = "10.18653/v1/2023.acl-long.620",
pages = "11067--11083",
abstract = "Many machine learning-based low-code or no-code applications involve generating code that interacts with structured knowledge. For example, one of the most studied tasks in this area is generating SQL code from a natural language statement. Prior work shows that incorporating context information from the database schema, such as table and column names, is beneficial to model performance on this task. In this work we present a large pretraining dataset and strategy for learning representations of text, tables, and SQL code that leverages the entire context of the problem. Specifically, we build on existing encoder-decoder architecture by introducing a multitask pretraining framework that complements the unique attributes of our diverse pretraining data. Our work represents the first study on large-scale pretraining of encoder-decoder models for interacting with structured knowledge, and offers a new state-of-the-art foundation model in text-to-SQL generation. We validate our approach with experiments on two SQL tasks, showing improvement over existing methods, including a 1.7 and 2.2 percentage point improvement over prior state-of-the-arts on Spider and CoSQL.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="giaquinto-etal-2023-multitask">
<titleInfo>
<title>Multitask Pretraining with Structured Knowledge for Text-to-SQL Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Giaquinto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dejiao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Kleiner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parminder</namePart>
<namePart type="family">Bhatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramesh</namePart>
<namePart type="family">Nallapati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaofei</namePart>
<namePart type="family">Ma</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>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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>Many machine learning-based low-code or no-code applications involve generating code that interacts with structured knowledge. For example, one of the most studied tasks in this area is generating SQL code from a natural language statement. Prior work shows that incorporating context information from the database schema, such as table and column names, is beneficial to model performance on this task. In this work we present a large pretraining dataset and strategy for learning representations of text, tables, and SQL code that leverages the entire context of the problem. Specifically, we build on existing encoder-decoder architecture by introducing a multitask pretraining framework that complements the unique attributes of our diverse pretraining data. Our work represents the first study on large-scale pretraining of encoder-decoder models for interacting with structured knowledge, and offers a new state-of-the-art foundation model in text-to-SQL generation. We validate our approach with experiments on two SQL tasks, showing improvement over existing methods, including a 1.7 and 2.2 percentage point improvement over prior state-of-the-arts on Spider and CoSQL.</abstract>
<identifier type="citekey">giaquinto-etal-2023-multitask</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.620</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.620</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>11067</start>
<end>11083</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multitask Pretraining with Structured Knowledge for Text-to-SQL Generation
%A Giaquinto, Robert
%A Zhang, Dejiao
%A Kleiner, Benjamin
%A Li, Yang
%A Tan, Ming
%A Bhatia, Parminder
%A Nallapati, Ramesh
%A Ma, Xiaofei
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F giaquinto-etal-2023-multitask
%X Many machine learning-based low-code or no-code applications involve generating code that interacts with structured knowledge. For example, one of the most studied tasks in this area is generating SQL code from a natural language statement. Prior work shows that incorporating context information from the database schema, such as table and column names, is beneficial to model performance on this task. In this work we present a large pretraining dataset and strategy for learning representations of text, tables, and SQL code that leverages the entire context of the problem. Specifically, we build on existing encoder-decoder architecture by introducing a multitask pretraining framework that complements the unique attributes of our diverse pretraining data. Our work represents the first study on large-scale pretraining of encoder-decoder models for interacting with structured knowledge, and offers a new state-of-the-art foundation model in text-to-SQL generation. We validate our approach with experiments on two SQL tasks, showing improvement over existing methods, including a 1.7 and 2.2 percentage point improvement over prior state-of-the-arts on Spider and CoSQL.
%R 10.18653/v1/2023.acl-long.620
%U https://aclanthology.org/2023.acl-long.620
%U https://doi.org/10.18653/v1/2023.acl-long.620
%P 11067-11083
Markdown (Informal)
[Multitask Pretraining with Structured Knowledge for Text-to-SQL Generation](https://aclanthology.org/2023.acl-long.620) (Giaquinto et al., ACL 2023)
ACL
- Robert Giaquinto, Dejiao Zhang, Benjamin Kleiner, Yang Li, Ming Tan, Parminder Bhatia, Ramesh Nallapati, and Xiaofei Ma. 2023. Multitask Pretraining with Structured Knowledge for Text-to-SQL Generation. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11067–11083, Toronto, Canada. Association for Computational Linguistics.