<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="takase-etal-2022-single">
    <titleInfo>
        <title>Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Sho</namePart>
        <namePart type="family">Takase</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Tatsuya</namePart>
        <namePart type="family">Hiraoka</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Naoaki</namePart>
        <namePart type="family">Okazaki</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2022-05</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Findings of the Association for Computational Linguistics: ACL 2022</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Smaranda</namePart>
            <namePart type="family">Muresan</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Preslav</namePart>
            <namePart type="family">Nakov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Aline</namePart>
            <namePart type="family">Villavicencio</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Dublin, Ireland</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Subword regularizations use multiple subword segmentations during training to improve the robustness of neural machine translation models. In previous subword regularizations, we use multiple segmentations in the training process but use only one segmentation in the inference. In this study, we propose an inference strategy to address this discrepancy. The proposed strategy approximates the marginalized likelihood by using multiple segmentations including the most plausible segmentation and several sampled segmentations. Because the proposed strategy aggregates predictions from several segmentations, we can regard it as a single model ensemble that does not require any additional cost for training. Experimental results show that the proposed strategy improves the performance of models trained with subword regularization in low-resource machine translation tasks.</abstract>
    <identifier type="citekey">takase-etal-2022-single</identifier>
    <identifier type="doi">10.18653/v1/2022.findings-acl.199</identifier>
    <location>
        <url>https://aclanthology.org/2022.findings-acl.199</url>
    </location>
    <part>
        <date>2022-05</date>
        <extent unit="page">
            <start>2536</start>
            <end>2541</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation
%A Takase, Sho
%A Hiraoka, Tatsuya
%A Okazaki, Naoaki
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F takase-etal-2022-single
%X Subword regularizations use multiple subword segmentations during training to improve the robustness of neural machine translation models. In previous subword regularizations, we use multiple segmentations in the training process but use only one segmentation in the inference. In this study, we propose an inference strategy to address this discrepancy. The proposed strategy approximates the marginalized likelihood by using multiple segmentations including the most plausible segmentation and several sampled segmentations. Because the proposed strategy aggregates predictions from several segmentations, we can regard it as a single model ensemble that does not require any additional cost for training. Experimental results show that the proposed strategy improves the performance of models trained with subword regularization in low-resource machine translation tasks.
%R 10.18653/v1/2022.findings-acl.199
%U https://aclanthology.org/2022.findings-acl.199
%U https://doi.org/10.18653/v1/2022.findings-acl.199
%P 2536-2541

Markdown (Informal)

[Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation](https://aclanthology.org/2022.findings-acl.199) (Takase et al., Findings 2022)

• Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation (Takase et al., Findings 2022)

ACL

• Sho Takase, Tatsuya Hiraoka, and Naoaki Okazaki. 2022. Single Model Ensemble for Subword Regularized Models in Low-Resource Machine Translation. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2536–2541, Dublin, Ireland. Association for Computational Linguistics.