<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kocmi-bojar-2017-curriculum">
    <titleInfo>
        <title>Curriculum Learning and Minibatch Bucketing in Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Tom</namePart>
        <namePart type="family">Kocmi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ond\v</namePart>
        <namePart type="given">rej</namePart>
        <namePart type="family">Bojar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd.</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>We examine the effects of particular orderings of sentence pairs on the on-line training of neural machine translation (NMT). We focus on two types of such orderings: (1) ensuring that each minibatch contains sentences similar in some aspect and (2) gradual inclusion of some sentence types as the training progresses (so called “curriculum learning”). In our English-to-Czech experiments, the internal homogeneity of minibatches has no effect on the training but some of our “curricula” achieve a small improvement over the baseline.</abstract>
    <identifier type="citekey">kocmi-bojar-2017-curriculum</identifier>
    <identifier type="doi">10.26615/978-954-452-049-6_050</identifier>
    <location>
        <url>https://aclanthology.org/R17-1050/</url>
    </location>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>379</start>
            <end>386</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Curriculum Learning and Minibatch Bucketing in Neural Machine Translation
%A Kocmi, Tom
%A Bojar, Ond\v rej
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
%D 2017
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F kocmi-bojar-2017-curriculum
%X We examine the effects of particular orderings of sentence pairs on the on-line training of neural machine translation (NMT). We focus on two types of such orderings: (1) ensuring that each minibatch contains sentences similar in some aspect and (2) gradual inclusion of some sentence types as the training progresses (so called “curriculum learning”). In our English-to-Czech experiments, the internal homogeneity of minibatches has no effect on the training but some of our “curricula” achieve a small improvement over the baseline.
%R 10.26615/978-954-452-049-6_050
%U https://aclanthology.org/R17-1050/
%U https://doi.org/10.26615/978-954-452-049-6_050
%P 379-386

Markdown (Informal)

[Curriculum Learning and Minibatch Bucketing in Neural Machine Translation](https://aclanthology.org/R17-1050/) (Kocmi & Bojar, RANLP 2017)

• Curriculum Learning and Minibatch Bucketing in Neural Machine Translation (Kocmi & Bojar, RANLP 2017)

ACL

• Tom Kocmi and Ondřej Bojar. 2017. Curriculum Learning and Minibatch Bucketing in Neural Machine Translation. In Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017, pages 379–386, Varna, Bulgaria. INCOMA Ltd..