<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="muller-sennrich-2021-understanding">
    <titleInfo>
        <title>Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mathias</namePart>
        <namePart type="family">Müller</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Rico</namePart>
        <namePart type="family">Sennrich</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Chengqing</namePart>
            <namePart type="family">Zong</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Fei</namePart>
            <namePart type="family">Xia</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Wenjie</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Roberto</namePart>
            <namePart type="family">Navigli</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Neural Machine Translation (NMT) currently exhibits biases such as producing translations that are too short and overgenerating frequent words, and shows poor robustness to copy noise in training data or domain shift. Recent work has tied these shortcomings to beam search – the de facto standard inference algorithm in NMT – and Eikema &amp; Aziz (2020) propose to use Minimum Bayes Risk (MBR) decoding on unbiased samples instead. In this paper, we empirically investigate the properties of MBR decoding on a number of previously reported biases and failure cases of beam search. We find that MBR still exhibits a length and token frequency bias, owing to the MT metrics used as utility functions, but that MBR also increases robustness against copy noise in the training data and domain shift.</abstract>
    <identifier type="citekey">muller-sennrich-2021-understanding</identifier>
    <identifier type="doi">10.18653/v1/2021.acl-long.22</identifier>
    <location>
        <url>https://aclanthology.org/2021.acl-long.22</url>
    </location>
    <part>
        <date>2021-08</date>
        <extent unit="page">
            <start>259</start>
            <end>272</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation
%A Müller, Mathias
%A Sennrich, Rico
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F muller-sennrich-2021-understanding
%X Neural Machine Translation (NMT) currently exhibits biases such as producing translations that are too short and overgenerating frequent words, and shows poor robustness to copy noise in training data or domain shift. Recent work has tied these shortcomings to beam search – the de facto standard inference algorithm in NMT – and Eikema & Aziz (2020) propose to use Minimum Bayes Risk (MBR) decoding on unbiased samples instead. In this paper, we empirically investigate the properties of MBR decoding on a number of previously reported biases and failure cases of beam search. We find that MBR still exhibits a length and token frequency bias, owing to the MT metrics used as utility functions, but that MBR also increases robustness against copy noise in the training data and domain shift.
%R 10.18653/v1/2021.acl-long.22
%U https://aclanthology.org/2021.acl-long.22
%U https://doi.org/10.18653/v1/2021.acl-long.22
%P 259-272

Markdown (Informal)

[Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation](https://aclanthology.org/2021.acl-long.22) (Müller & Sennrich, ACL-IJCNLP 2021)

• Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation (Müller & Sennrich, ACL-IJCNLP 2021)

ACL

• Mathias Müller and Rico Sennrich. 2021. Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 259–272, Online. Association for Computational Linguistics.