<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-etal-2021-learning-curricula">
    <titleInfo>
        <title>Learning Curricula for Multilingual Neural Machine Translation Training</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Gaurav</namePart>
        <namePart type="family">Kumar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Philipp</namePart>
        <namePart type="family">Koehn</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Sanjeev</namePart>
        <namePart type="family">Khudanpur</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 Machine Translation Summit XVIII: Research Track</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Kevin</namePart>
            <namePart type="family">Duh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Francisco</namePart>
            <namePart type="family">Guzmán</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Machine Translation in the Americas</publisher>
            <place>
                <placeTerm type="text">Virtual</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs. In this paper and we propose two simple search based curricula – orderings of the multilingual training data – which help improve translation performance in conjunction with existing techniques such as fine-tuning. Additionally and we attempt to learn a curriculum for MNMT from scratch jointly with the training of the translation system using contextual multi-arm bandits. We show on the FLORES low-resource translation dataset that these learned curricula can provide better starting points for fine tuning and improve overall performance of the translation system.</abstract>
    <identifier type="citekey">kumar-etal-2021-learning-curricula</identifier>
    <location>
        <url>https://aclanthology.org/2021.mtsummit-research.1</url>
    </location>
    <part>
        <date>2021-08</date>
        <extent unit="page">
            <start>1</start>
            <end>9</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Learning Curricula for Multilingual Neural Machine Translation Training
%A Kumar, Gaurav
%A Koehn, Philipp
%A Khudanpur, Sanjeev
%Y Duh, Kevin
%Y Guzmán, Francisco
%S Proceedings of Machine Translation Summit XVIII: Research Track
%D 2021
%8 August
%I Association for Machine Translation in the Americas
%C Virtual
%F kumar-etal-2021-learning-curricula
%X Low-resource Multilingual Neural Machine Translation (MNMT) is typically tasked with improving the translation performance on one or more language pairs with the aid of high-resource language pairs. In this paper and we propose two simple search based curricula – orderings of the multilingual training data – which help improve translation performance in conjunction with existing techniques such as fine-tuning. Additionally and we attempt to learn a curriculum for MNMT from scratch jointly with the training of the translation system using contextual multi-arm bandits. We show on the FLORES low-resource translation dataset that these learned curricula can provide better starting points for fine tuning and improve overall performance of the translation system.
%U https://aclanthology.org/2021.mtsummit-research.1
%P 1-9

Markdown (Informal)

[Learning Curricula for Multilingual Neural Machine Translation Training](https://aclanthology.org/2021.mtsummit-research.1) (Kumar et al., MTSummit 2021)

• Learning Curricula for Multilingual Neural Machine Translation Training (Kumar et al., MTSummit 2021)

ACL

• Gaurav Kumar, Philipp Koehn, and Sanjeev Khudanpur. 2021. Learning Curricula for Multilingual Neural Machine Translation Training. In Proceedings of Machine Translation Summit XVIII: Research Track, pages 1–9, Virtual. Association for Machine Translation in the Americas.