<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-etal-2022-sead">
    <titleInfo>
        <title>SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Kuan</namePart>
        <namePart type="family">Xu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yongbo</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yongliang</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zihao</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zujie</namePart>
        <namePart type="family">Wen</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Dong</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Marine</namePart>
            <namePart type="family">Carpuat</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Marie-Catherine</namePart>
            <namePart type="family">de Marneffe</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Ivan</namePart>
            <namePart type="given">Vladimir</namePart>
            <namePart type="family">Meza Ruiz</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Seattle, United States</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>On the WikiSQL benchmark, most methods tackle the challenge of text-to-SQL with predefined sketch slots and build sophisticated sub-tasks to fill these slots. Though achieving promising results, these methods suffer from over-complex model structure. In this paper, we present a simple yet effective approach that enables auto-regressive sequence-to-sequence model to robust text-to-SQL generation. Instead of formulating the task of text-to-SQL as slot-filling, we propose to train sequence-to-sequence model with Schema-aware Denoising (SeaD), which consists of two denoising objectives that train model to either recover input or predict output from two novel erosion and shuffle noises. These model-agnostic denoising objectives act as the auxiliary tasks for structural data modeling during sequence-to-sequence generation. In addition, we propose a clause-sensitive execution guided (EG) decoding strategy to overcome the limitation of EG decoding for generative model. The experiments show that the proposed method improves the performance of sequence-to-sequence model in both schema linking and grammar correctness and establishes new state-of-the-art on WikiSQL benchmark. Our work indicates that the capacity of sequence-to-sequence model for text-to-SQL may have been under-estimated and could be enhanced by specialized denoising task.</abstract>
    <identifier type="citekey">xu-etal-2022-sead</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-naacl.141</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-naacl.141</url>
    </location>
    <part>
        <date>2022-07</date>
        <extent unit="page">
            <start>1845</start>
            <end>1853</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising
%A Xu, Kuan
%A Wang, Yongbo
%A Wang, Yongliang
%A Wang, Zihao
%A Wen, Zujie
%A Dong, Yang
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F xu-etal-2022-sead
%X On the WikiSQL benchmark, most methods tackle the challenge of text-to-SQL with predefined sketch slots and build sophisticated sub-tasks to fill these slots. Though achieving promising results, these methods suffer from over-complex model structure. In this paper, we present a simple yet effective approach that enables auto-regressive sequence-to-sequence model to robust text-to-SQL generation. Instead of formulating the task of text-to-SQL as slot-filling, we propose to train sequence-to-sequence model with Schema-aware Denoising (SeaD), which consists of two denoising objectives that train model to either recover input or predict output from two novel erosion and shuffle noises. These model-agnostic denoising objectives act as the auxiliary tasks for structural data modeling during sequence-to-sequence generation. In addition, we propose a clause-sensitive execution guided (EG) decoding strategy to overcome the limitation of EG decoding for generative model. The experiments show that the proposed method improves the performance of sequence-to-sequence model in both schema linking and grammar correctness and establishes new state-of-the-art on WikiSQL benchmark. Our work indicates that the capacity of sequence-to-sequence model for text-to-SQL may have been under-estimated and could be enhanced by specialized denoising task.
%R 10.18653/v1/2022.findings-naacl.141
%U https://aclanthology.org/2022.findings-naacl.141
%U https://doi.org/10.18653/v1/2022.findings-naacl.141
%P 1845-1853

Markdown (Informal)

[SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising](https://aclanthology.org/2022.findings-naacl.141) (Xu et al., Findings 2022)

• SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising (Xu et al., Findings 2022)

ACL

• Kuan Xu, Yongbo Wang, Yongliang Wang, Zihao Wang, Zujie Wen, and Yang Dong. 2022. SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1845–1853, Seattle, United States. Association for Computational Linguistics.