<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kaneko-etal-2020-encoder">
    <titleInfo>
        <title>Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Masahiro</namePart>
        <namePart type="family">Kaneko</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Masato</namePart>
        <namePart type="family">Mita</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shun</namePart>
        <namePart type="family">Kiyono</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jun</namePart>
        <namePart type="family">Suzuki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kentaro</namePart>
        <namePart type="family">Inui</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-07</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper investigates how to effectively incorporate a pre-trained masked language model (MLM), such as BERT, into an encoder-decoder (EncDec) model for grammatical error correction (GEC). The answer to this question is not as straightforward as one might expect because the previous common methods for incorporating a MLM into an EncDec model have potential drawbacks when applied to GEC. For example, the distribution of the inputs to a GEC model can be considerably different (erroneous, clumsy, etc.) from that of the corpora used for pre-training MLMs; however, this issue is not addressed in the previous methods. Our experiments show that our proposed method, where we first fine-tune a MLM with a given GEC corpus and then use the output of the fine-tuned MLM as additional features in the GEC model, maximizes the benefit of the MLM. The best-performing model achieves state-of-the-art performances on the BEA-2019 and CoNLL-2014 benchmarks. Our code is publicly available at: https://github.com/kanekomasahiro/bert-gec.</abstract>
    <identifier type="citekey">kaneko-etal-2020-encoder</identifier>
    <identifier type="doi">10.18653/v1/2020.acl-main.391</identifier>
    <location>
        <url>https://aclanthology.org/2020.acl-main.391</url>
    </location>
    <part>
        <date>2020-07</date>
        <extent unit="page">
            <start>4248</start>
            <end>4254</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction
%A Kaneko, Masahiro
%A Mita, Masato
%A Kiyono, Shun
%A Suzuki, Jun
%A Inui, Kentaro
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F kaneko-etal-2020-encoder
%X This paper investigates how to effectively incorporate a pre-trained masked language model (MLM), such as BERT, into an encoder-decoder (EncDec) model for grammatical error correction (GEC). The answer to this question is not as straightforward as one might expect because the previous common methods for incorporating a MLM into an EncDec model have potential drawbacks when applied to GEC. For example, the distribution of the inputs to a GEC model can be considerably different (erroneous, clumsy, etc.) from that of the corpora used for pre-training MLMs; however, this issue is not addressed in the previous methods. Our experiments show that our proposed method, where we first fine-tune a MLM with a given GEC corpus and then use the output of the fine-tuned MLM as additional features in the GEC model, maximizes the benefit of the MLM. The best-performing model achieves state-of-the-art performances on the BEA-2019 and CoNLL-2014 benchmarks. Our code is publicly available at: https://github.com/kanekomasahiro/bert-gec.
%R 10.18653/v1/2020.acl-main.391
%U https://aclanthology.org/2020.acl-main.391
%U https://doi.org/10.18653/v1/2020.acl-main.391
%P 4248-4254

Markdown (Informal)

[Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction](https://aclanthology.org/2020.acl-main.391) (Kaneko et al., ACL 2020)

• Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction (Kaneko et al., ACL 2020)

ACL

• Masahiro Kaneko, Masato Mita, Shun Kiyono, Jun Suzuki, and Kentaro Inui. 2020. Encoder-Decoder Models Can Benefit from Pre-trained Masked Language Models in Grammatical Error Correction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4248–4254, Online. Association for Computational Linguistics.