<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jasim-etal-2020-phraseout">
    <titleInfo>
        <title>PhraseOut: A Code Mixed Data Augmentation Method for MultilingualNeural Machine Tranlsation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Binu</namePart>
        <namePart type="family">Jasim</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Vinay</namePart>
        <namePart type="family">Namboodiri</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">C</namePart>
        <namePart type="given">V</namePart>
        <namePart type="family">Jawahar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 17th International Conference on Natural Language Processing (ICON)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Pushpak</namePart>
            <namePart type="family">Bhattacharyya</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Dipti</namePart>
            <namePart type="given">Misra</namePart>
            <namePart type="family">Sharma</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rajeev</namePart>
            <namePart type="family">Sangal</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>NLP Association of India (NLPAI)</publisher>
            <place>
                <placeTerm type="text">Indian Institute of Technology Patna, Patna, India</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Data Augmentation methods for Neural Machine Translation (NMT) such as back- translation (BT) and self-training (ST) are quite popular. In a multilingual NMT system, simply copying monolingual source sentences to the target (Copying) is an effective data augmentation method. Back-translation aug- ments parallel data by translating monolingual sentences in the target side to source language. In this work we propose to use a partial back- translation method in a multilingual setting. Instead of translating the entire monolingual target sentence back into the source language, we replace selected high confidence phrases only and keep the rest of the words in the target language itself. (We call this method PhraseOut). Our experiments on low resource multilingual translation models show that PhraseOut gives reasonable improvements over the existing data augmentation methods.</abstract>
    <identifier type="citekey">jasim-etal-2020-phraseout</identifier>
    <location>
        <url>https://aclanthology.org/2020.icon-main.63</url>
    </location>
    <part>
        <date>2020-12</date>
        <extent unit="page">
            <start>470</start>
            <end>474</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T PhraseOut: A Code Mixed Data Augmentation Method for MultilingualNeural Machine Tranlsation
%A Jasim, Binu
%A Namboodiri, Vinay
%A Jawahar, C. V.
%Y Bhattacharyya, Pushpak
%Y Sharma, Dipti Misra
%Y Sangal, Rajeev
%S Proceedings of the 17th International Conference on Natural Language Processing (ICON)
%D 2020
%8 December
%I NLP Association of India (NLPAI)
%C Indian Institute of Technology Patna, Patna, India
%F jasim-etal-2020-phraseout
%X Data Augmentation methods for Neural Machine Translation (NMT) such as back- translation (BT) and self-training (ST) are quite popular. In a multilingual NMT system, simply copying monolingual source sentences to the target (Copying) is an effective data augmentation method. Back-translation aug- ments parallel data by translating monolingual sentences in the target side to source language. In this work we propose to use a partial back- translation method in a multilingual setting. Instead of translating the entire monolingual target sentence back into the source language, we replace selected high confidence phrases only and keep the rest of the words in the target language itself. (We call this method PhraseOut). Our experiments on low resource multilingual translation models show that PhraseOut gives reasonable improvements over the existing data augmentation methods.
%U https://aclanthology.org/2020.icon-main.63
%P 470-474

Markdown (Informal)

[PhraseOut: A Code Mixed Data Augmentation Method for MultilingualNeural Machine Tranlsation](https://aclanthology.org/2020.icon-main.63) (Jasim et al., ICON 2020)

• PhraseOut: A Code Mixed Data Augmentation Method for MultilingualNeural Machine Tranlsation (Jasim et al., ICON 2020)

ACL

• Binu Jasim, Vinay Namboodiri, and C V Jawahar. 2020. PhraseOut: A Code Mixed Data Augmentation Method for MultilingualNeural Machine Tranlsation. In Proceedings of the 17th International Conference on Natural Language Processing (ICON), pages 470–474, Indian Institute of Technology Patna, Patna, India. NLP Association of India (NLPAI).