@inproceedings{awasthi-etal-2022-diverse,
title = "Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-{SQL} Parsers",
author = "Awasthi, Abhijeet and
Sathe, Ashutosh and
Sarawagi, Sunita",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.794/",
doi = "10.18653/v1/2022.emnlp-main.794",
pages = "11548--11562",
abstract = "Text-to-SQL parsers typically struggle with databases unseen during the train time. Adapting Text-to-SQL parsers to new database schemas is a challenging problem owing to a vast diversity of schemas and zero availability of natural language queries in new schemas. We present ReFill, a framework for synthesizing high-quality and textually diverse parallel datasets for adapting Text-to-SQL parsers. Unlike prior methods that utilize SQL-to-Text generation, ReFill learns to retrieve-and-edit text queries in existing schemas and transfer them to the new schema. ReFill utilizes a simple method for retrieving diverse existing text, masking their schema-specific tokens, and refilling with tokens relevant to the new schema. We show that this process leads to significantly more diverse text queries than achievable by standard SQL-to-Text generation models. Through experiments on several databases, we show that adapting a parser by finetuning it on datasets synthesized by ReFill consistently outperforms prior data-augmentation methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="awasthi-etal-2022-diverse">
<titleInfo>
<title>Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parsers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhijeet</namePart>
<namePart type="family">Awasthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashutosh</namePart>
<namePart type="family">Sathe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunita</namePart>
<namePart type="family">Sarawagi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text-to-SQL parsers typically struggle with databases unseen during the train time. Adapting Text-to-SQL parsers to new database schemas is a challenging problem owing to a vast diversity of schemas and zero availability of natural language queries in new schemas. We present ReFill, a framework for synthesizing high-quality and textually diverse parallel datasets for adapting Text-to-SQL parsers. Unlike prior methods that utilize SQL-to-Text generation, ReFill learns to retrieve-and-edit text queries in existing schemas and transfer them to the new schema. ReFill utilizes a simple method for retrieving diverse existing text, masking their schema-specific tokens, and refilling with tokens relevant to the new schema. We show that this process leads to significantly more diverse text queries than achievable by standard SQL-to-Text generation models. Through experiments on several databases, we show that adapting a parser by finetuning it on datasets synthesized by ReFill consistently outperforms prior data-augmentation methods.</abstract>
<identifier type="citekey">awasthi-etal-2022-diverse</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.794</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.794/</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>11548</start>
<end>11562</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parsers
%A Awasthi, Abhijeet
%A Sathe, Ashutosh
%A Sarawagi, Sunita
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F awasthi-etal-2022-diverse
%X Text-to-SQL parsers typically struggle with databases unseen during the train time. Adapting Text-to-SQL parsers to new database schemas is a challenging problem owing to a vast diversity of schemas and zero availability of natural language queries in new schemas. We present ReFill, a framework for synthesizing high-quality and textually diverse parallel datasets for adapting Text-to-SQL parsers. Unlike prior methods that utilize SQL-to-Text generation, ReFill learns to retrieve-and-edit text queries in existing schemas and transfer them to the new schema. ReFill utilizes a simple method for retrieving diverse existing text, masking their schema-specific tokens, and refilling with tokens relevant to the new schema. We show that this process leads to significantly more diverse text queries than achievable by standard SQL-to-Text generation models. Through experiments on several databases, we show that adapting a parser by finetuning it on datasets synthesized by ReFill consistently outperforms prior data-augmentation methods.
%R 10.18653/v1/2022.emnlp-main.794
%U https://aclanthology.org/2022.emnlp-main.794/
%U https://doi.org/10.18653/v1/2022.emnlp-main.794
%P 11548-11562
Markdown (Informal)
[Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parsers](https://aclanthology.org/2022.emnlp-main.794/) (Awasthi et al., EMNLP 2022)
ACL