<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gordon-etal-2021-data">
    <titleInfo>
        <title>Data and Parameter Scaling Laws for Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Mitchell</namePart>
        <namePart type="given">A</namePart>
        <namePart type="family">Gordon</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Kevin</namePart>
        <namePart type="family">Duh</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jared</namePart>
        <namePart type="family">Kaplan</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We observe that the development cross-entropy loss of supervised neural machine translation models scales like a power law with the amount of training data and the number of non-embedding parameters in the model. We discuss some practical implications of these results, such as predicting BLEU achieved by large scale models and predicting the ROI of labeling data in low-resource language pairs.</abstract>
    <identifier type="citekey">gordon-etal-2021-data</identifier>
    <identifier type="doi">10.18653/v1/2021.emnlp-main.478</identifier>
    <location>
        <url>https://aclanthology.org/2021.emnlp-main.478</url>
    </location>
    <part>
        <date>2021-11</date>
        <extent unit="page">
            <start>5915</start>
            <end>5922</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Data and Parameter Scaling Laws for Neural Machine Translation
%A Gordon, Mitchell A.
%A Duh, Kevin
%A Kaplan, Jared
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F gordon-etal-2021-data
%X We observe that the development cross-entropy loss of supervised neural machine translation models scales like a power law with the amount of training data and the number of non-embedding parameters in the model. We discuss some practical implications of these results, such as predicting BLEU achieved by large scale models and predicting the ROI of labeling data in low-resource language pairs.
%R 10.18653/v1/2021.emnlp-main.478
%U https://aclanthology.org/2021.emnlp-main.478
%U https://doi.org/10.18653/v1/2021.emnlp-main.478
%P 5915-5922

Markdown (Informal)

[Data and Parameter Scaling Laws for Neural Machine Translation](https://aclanthology.org/2021.emnlp-main.478) (Gordon et al., EMNLP 2021)

• Data and Parameter Scaling Laws for Neural Machine Translation (Gordon et al., EMNLP 2021)

ACL

• Mitchell A Gordon, Kevin Duh, and Jared Kaplan. 2021. Data and Parameter Scaling Laws for Neural Machine Translation. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 5915–5922, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.