<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saparina-lapata-2024-improving">
    <titleInfo>
        <title>Improving Generalization in Semantic Parsing by Increasing Natural Language Variation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Irina</namePart>
        <namePart type="family">Saparina</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Mirella</namePart>
        <namePart type="family">Lapata</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2024-03</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yvette</namePart>
            <namePart type="family">Graham</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Matthew</namePart>
            <namePart type="family">Purver</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">St. Julian’s, Malta</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Text-to-SQL semantic parsing has made significant progress in recent years, with various models demonstrating impressive performance on the challenging Spider benchmark. However, it has also been shown that these models often struggle to generalize even when faced with small perturbations of previously (accurately) parsed expressions. This is mainly due to the linguistic form of questions in Spider which are overly specific, unnatural, and display limited variation. In this work, we use data augmentation to enhance the robustness of text-to-SQL parsers against natural language variations. Existing approaches generate question reformulations either via models trained on Spider or only introduce local changes. In contrast, we leverage the capabilities of large language models to generate more realistic and diverse questions. Using only a few prompts, we achieve a two-fold increase in the number of questions in Spider. Training on this augmented dataset yields substantial improvements on a range of evaluation sets, including robustness benchmarks and out-of-domain data.</abstract>
    <identifier type="citekey">saparina-lapata-2024-improving</identifier>
    <location>
        <url>https://aclanthology.org/2024.eacl-long.71</url>
    </location>
    <part>
        <date>2024-03</date>
        <extent unit="page">
            <start>1178</start>
            <end>1193</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Improving Generalization in Semantic Parsing by Increasing Natural Language Variation
%A Saparina, Irina
%A Lapata, Mirella
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F saparina-lapata-2024-improving
%X Text-to-SQL semantic parsing has made significant progress in recent years, with various models demonstrating impressive performance on the challenging Spider benchmark. However, it has also been shown that these models often struggle to generalize even when faced with small perturbations of previously (accurately) parsed expressions. This is mainly due to the linguistic form of questions in Spider which are overly specific, unnatural, and display limited variation. In this work, we use data augmentation to enhance the robustness of text-to-SQL parsers against natural language variations. Existing approaches generate question reformulations either via models trained on Spider or only introduce local changes. In contrast, we leverage the capabilities of large language models to generate more realistic and diverse questions. Using only a few prompts, we achieve a two-fold increase in the number of questions in Spider. Training on this augmented dataset yields substantial improvements on a range of evaluation sets, including robustness benchmarks and out-of-domain data.
%U https://aclanthology.org/2024.eacl-long.71
%P 1178-1193

Markdown (Informal)

[Improving Generalization in Semantic Parsing by Increasing Natural Language Variation](https://aclanthology.org/2024.eacl-long.71) (Saparina & Lapata, EACL 2024)

• Improving Generalization in Semantic Parsing by Increasing Natural Language Variation (Saparina & Lapata, EACL 2024)

ACL

• Irina Saparina and Mirella Lapata. 2024. Improving Generalization in Semantic Parsing by Increasing Natural Language Variation. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1178–1193, St. Julian’s, Malta. Association for Computational Linguistics.