<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="beloucif-etal-2019-naive">
    <titleInfo>
        <title>Naive Regularizers for Low-Resource Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Meriem</namePart>
        <namePart type="family">Beloucif</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ana</namePart>
        <namePart type="given">Valeria</namePart>
        <namePart type="family">Gonzalez</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Marcel</namePart>
        <namePart type="family">Bollmann</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Anders</namePart>
        <namePart type="family">Søgaard</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2019-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)</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>Neural machine translation models have little inductive bias, which can be a disadvantage in low-resource scenarios. Neural models have to be trained on large amounts of data and have been shown to perform poorly when only limited data is available. We show that using naive regularization methods, based on sentence length, punctuation and word frequencies, to penalize translations that are very different from the input sentences, consistently improves the translation quality across multiple low-resource languages. We experiment with 12 language pairs, varying the training data size between 17k to 230k sentence pairs. Our best regularizer achieves an average increase of 1.5 BLEU score and 1.0 TER score across all the language pairs. For example, we achieve a BLEU score of 26.70 on the IWSLT15 English–Vietnamese translation task simply by using relative differences in punctuation as a regularizer.</abstract>
    <identifier type="citekey">beloucif-etal-2019-naive</identifier>
    <identifier type="doi">10.26615/978-954-452-056-4_013</identifier>
    <location>
        <url>https://aclanthology.org/R19-1013</url>
    </location>
    <part>
        <date>2019-09</date>
        <extent unit="page">
            <start>102</start>
            <end>111</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Naive Regularizers for Low-Resource Neural Machine Translation
%A Beloucif, Meriem
%A Gonzalez, Ana Valeria
%A Bollmann, Marcel
%A Søgaard, Anders
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
%D 2019
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F beloucif-etal-2019-naive
%X Neural machine translation models have little inductive bias, which can be a disadvantage in low-resource scenarios. Neural models have to be trained on large amounts of data and have been shown to perform poorly when only limited data is available. We show that using naive regularization methods, based on sentence length, punctuation and word frequencies, to penalize translations that are very different from the input sentences, consistently improves the translation quality across multiple low-resource languages. We experiment with 12 language pairs, varying the training data size between 17k to 230k sentence pairs. Our best regularizer achieves an average increase of 1.5 BLEU score and 1.0 TER score across all the language pairs. For example, we achieve a BLEU score of 26.70 on the IWSLT15 English–Vietnamese translation task simply by using relative differences in punctuation as a regularizer.
%R 10.26615/978-954-452-056-4_013
%U https://aclanthology.org/R19-1013
%U https://doi.org/10.26615/978-954-452-056-4_013
%P 102-111

Markdown (Informal)

[Naive Regularizers for Low-Resource Neural Machine Translation](https://aclanthology.org/R19-1013) (Beloucif et al., RANLP 2019)

• Naive Regularizers for Low-Resource Neural Machine Translation (Beloucif et al., RANLP 2019)

ACL

• Meriem Beloucif, Ana Valeria Gonzalez, Marcel Bollmann, and Anders Søgaard. 2019. Naive Regularizers for Low-Resource Neural Machine Translation. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 102–111, Varna, Bulgaria. INCOMA Ltd..