<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-etal-2022-semantically">
    <titleInfo>
        <title>Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Qiao</namePart>
        <namePart type="family">Cheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jin</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yitao</namePart>
        <namePart type="family">Duan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 29th International Conference on Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <publisher>International Committee on Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>This paper introduces a new data augmentation method for neural machine translation that can enforce stronger semantic consistency both within and across languages. Our method is based on Conditional Masked Language Model (CMLM) which is bi-directional and can be conditional on both left and right context, as well as the label. We demonstrate that CMLM is a good technique for generating context-dependent word distributions. In particular, we show that CMLM is capable of enforcing semantic consistency by conditioning on both source and target during substitution. In addition, to enhance diversity, we incorporate the idea of soft word substitution for data augmentation which replaces a word with a probabilistic distribution over the vocabulary. Experiments on four translation datasets of different scales show that the overall solution results in more realistic data augmentation and better translation quality. Our approach consistently achieves the best performance in comparison with strong and recent works and yields improvements of up to 1.90 BLEU points over the baseline.</abstract>
    <identifier type="citekey">cheng-etal-2022-semantically</identifier>
    <location>
        <url>https://aclanthology.org/2022.coling-1.457</url>
    </location>
    <part>
        <date>2022-10</date>
        <extent unit="page">
            <start>5148</start>
            <end>5157</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model
%A Cheng, Qiao
%A Huang, Jin
%A Duan, Yitao
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F cheng-etal-2022-semantically
%X This paper introduces a new data augmentation method for neural machine translation that can enforce stronger semantic consistency both within and across languages. Our method is based on Conditional Masked Language Model (CMLM) which is bi-directional and can be conditional on both left and right context, as well as the label. We demonstrate that CMLM is a good technique for generating context-dependent word distributions. In particular, we show that CMLM is capable of enforcing semantic consistency by conditioning on both source and target during substitution. In addition, to enhance diversity, we incorporate the idea of soft word substitution for data augmentation which replaces a word with a probabilistic distribution over the vocabulary. Experiments on four translation datasets of different scales show that the overall solution results in more realistic data augmentation and better translation quality. Our approach consistently achieves the best performance in comparison with strong and recent works and yields improvements of up to 1.90 BLEU points over the baseline.
%U https://aclanthology.org/2022.coling-1.457
%P 5148-5157

Markdown (Informal)

[Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model](https://aclanthology.org/2022.coling-1.457) (Cheng et al., COLING 2022)

• Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model (Cheng et al., COLING 2022)

ACL

• Qiao Cheng, Jin Huang, and Yitao Duan. 2022. Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5148–5157, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.