<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cheng-vlachos-2023-faster">
    <titleInfo>
        <title>Faster Minimum Bayes Risk Decoding with Confidence-based Pruning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Julius</namePart>
        <namePart type="family">Cheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Andreas</namePart>
        <namePart type="family">Vlachos</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2023-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Houda</namePart>
            <namePart type="family">Bouamor</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Juan</namePart>
            <namePart type="family">Pino</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Kalika</namePart>
            <namePart type="family">Bali</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Singapore</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Minimum Bayes risk (MBR) decoding outputs the hypothesis with the highest expected utility over the model distribution for some utility function. It has been shown to improve accuracy over beam search in conditional language generation problems and especially neural machine translation, in both human and automatic evaluations. However, the standard sampling-based algorithm for MBR is substantially more computationally expensive than beam search, requiring a large number of samples as well as a quadratic number of calls to the utility function, limiting its applicability. We describe an algorithm for MBR which gradually grows the number of samples used to estimate the utility while pruning hypotheses that are unlikely to have the highest utility according to confidence estimates obtained with bootstrap sampling. Our method requires fewer samples and drastically reduces the number of calls to the utility function compared to standard MBR while being statistically indistinguishable in terms of accuracy. We demonstrate the effectiveness of our approach in experiments on three language pairs, using chrF++ and COMET as utility/evaluation metrics.</abstract>
    <identifier type="citekey">cheng-vlachos-2023-faster</identifier>
    <identifier type="doi">10.18653/v1/2023.emnlp-main.767</identifier>
    <location>
        <url>https://aclanthology.org/2023.emnlp-main.767</url>
    </location>
    <part>
        <date>2023-12</date>
        <extent unit="page">
            <start>12473</start>
            <end>12480</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Faster Minimum Bayes Risk Decoding with Confidence-based Pruning
%A Cheng, Julius
%A Vlachos, Andreas
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F cheng-vlachos-2023-faster
%X Minimum Bayes risk (MBR) decoding outputs the hypothesis with the highest expected utility over the model distribution for some utility function. It has been shown to improve accuracy over beam search in conditional language generation problems and especially neural machine translation, in both human and automatic evaluations. However, the standard sampling-based algorithm for MBR is substantially more computationally expensive than beam search, requiring a large number of samples as well as a quadratic number of calls to the utility function, limiting its applicability. We describe an algorithm for MBR which gradually grows the number of samples used to estimate the utility while pruning hypotheses that are unlikely to have the highest utility according to confidence estimates obtained with bootstrap sampling. Our method requires fewer samples and drastically reduces the number of calls to the utility function compared to standard MBR while being statistically indistinguishable in terms of accuracy. We demonstrate the effectiveness of our approach in experiments on three language pairs, using chrF++ and COMET as utility/evaluation metrics.
%R 10.18653/v1/2023.emnlp-main.767
%U https://aclanthology.org/2023.emnlp-main.767
%U https://doi.org/10.18653/v1/2023.emnlp-main.767
%P 12473-12480

Markdown (Informal)

[Faster Minimum Bayes Risk Decoding with Confidence-based Pruning](https://aclanthology.org/2023.emnlp-main.767) (Cheng & Vlachos, EMNLP 2023)

• Faster Minimum Bayes Risk Decoding with Confidence-based Pruning (Cheng & Vlachos, EMNLP 2023)

ACL

• Julius Cheng and Andreas Vlachos. 2023. Faster Minimum Bayes Risk Decoding with Confidence-based Pruning. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12473–12480, Singapore. Association for Computational Linguistics.