<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tan-etal-2023-focal">
    <titleInfo>
        <title>Focal Training and Tagger Decouple for Grammatical Error Correction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Minghuan</namePart>
        <namePart type="family">Tan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Min</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ruifeng</namePart>
        <namePart type="family">Xu</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>Findings of the Association for Computational Linguistics: ACL 2023</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>In this paper, we investigate how to improve tagging-based Grammatical Error Correction models. We address two issues of current tagging-based approaches, label imbalance issue, and tagging entanglement issue. Then we propose to down-weight the loss of well-classified labels using Focal Loss and decouple the error detection layer from the label tagging layer through an extra self-attention-based matching module. Experiments over three latest Chinese Grammatical Error Correction datasets show that our proposed methods are effective. We further analyze choices of hyper-parameters for Focal Loss and inference tweaking.</abstract>
    <identifier type="citekey">tan-etal-2023-focal</identifier>
    <identifier type="doi">10.18653/v1/2023.findings-acl.370</identifier>
    <location>
        <url>https://aclanthology.org/2023.findings-acl.370/</url>
    </location>
    <part>
        <date>2023-07</date>
        <extent unit="page">
            <start>5978</start>
            <end>5985</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Focal Training and Tagger Decouple for Grammatical Error Correction
%A Tan, Minghuan
%A Yang, Min
%A Xu, Ruifeng
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F tan-etal-2023-focal
%X In this paper, we investigate how to improve tagging-based Grammatical Error Correction models. We address two issues of current tagging-based approaches, label imbalance issue, and tagging entanglement issue. Then we propose to down-weight the loss of well-classified labels using Focal Loss and decouple the error detection layer from the label tagging layer through an extra self-attention-based matching module. Experiments over three latest Chinese Grammatical Error Correction datasets show that our proposed methods are effective. We further analyze choices of hyper-parameters for Focal Loss and inference tweaking.
%R 10.18653/v1/2023.findings-acl.370
%U https://aclanthology.org/2023.findings-acl.370/
%U https://doi.org/10.18653/v1/2023.findings-acl.370
%P 5978-5985

Markdown (Informal)

[Focal Training and Tagger Decouple for Grammatical Error Correction](https://aclanthology.org/2023.findings-acl.370/) (Tan et al., Findings 2023)

• Focal Training and Tagger Decouple for Grammatical Error Correction (Tan et al., Findings 2023)

ACL

• Minghuan Tan, Min Yang, and Ruifeng Xu. 2023. Focal Training and Tagger Decouple for Grammatical Error Correction. In Findings of the Association for Computational Linguistics: ACL 2023, pages 5978–5985, Toronto, Canada. Association for Computational Linguistics.