@inproceedings{nguyen-etal-2021-data,
title = "Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution",
author = "Nguyen, Toan Q. and
Murray, Kenton and
Chiang, David",
editor = "Federico, Marcello and
Waibel, Alex and
Costa-juss{\`a}, Marta R. and
Niehues, Jan and
Stuker, Sebastian and
Salesky, Elizabeth",
booktitle = "Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)",
month = aug,
year = "2021",
address = "Bangkok, Thailand (online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.iwslt-1.33",
doi = "10.18653/v1/2021.iwslt-1.33",
pages = "287--293",
abstract = "In this paper, we investigate the driving factors behind concatenation, a simple but effective data augmentation method for low-resource neural machine translation. Our experiments suggest that discourse context is unlikely the cause for concatenation improving BLEU by about +1 across four language pairs. Instead, we demonstrate that the improvement comes from three other factors unrelated to discourse: context diversity, length diversity, and (to a lesser extent) position shifting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2021-data">
<titleInfo>
<title>Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution</title>
</titleInfo>
<name type="personal">
<namePart type="given">Toan</namePart>
<namePart type="given">Q</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenton</namePart>
<namePart type="family">Murray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</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 the 18th International Conference on Spoken Language Translation (IWSLT 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Waibel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Niehues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Stuker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we investigate the driving factors behind concatenation, a simple but effective data augmentation method for low-resource neural machine translation. Our experiments suggest that discourse context is unlikely the cause for concatenation improving BLEU by about +1 across four language pairs. Instead, we demonstrate that the improvement comes from three other factors unrelated to discourse: context diversity, length diversity, and (to a lesser extent) position shifting.</abstract>
<identifier type="citekey">nguyen-etal-2021-data</identifier>
<identifier type="doi">10.18653/v1/2021.iwslt-1.33</identifier>
<location>
<url>https://aclanthology.org/2021.iwslt-1.33</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>287</start>
<end>293</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution
%A Nguyen, Toan Q.
%A Murray, Kenton
%A Chiang, David
%Y Federico, Marcello
%Y Waibel, Alex
%Y Costa-jussà, Marta R.
%Y Niehues, Jan
%Y Stuker, Sebastian
%Y Salesky, Elizabeth
%S Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand (online)
%F nguyen-etal-2021-data
%X In this paper, we investigate the driving factors behind concatenation, a simple but effective data augmentation method for low-resource neural machine translation. Our experiments suggest that discourse context is unlikely the cause for concatenation improving BLEU by about +1 across four language pairs. Instead, we demonstrate that the improvement comes from three other factors unrelated to discourse: context diversity, length diversity, and (to a lesser extent) position shifting.
%R 10.18653/v1/2021.iwslt-1.33
%U https://aclanthology.org/2021.iwslt-1.33
%U https://doi.org/10.18653/v1/2021.iwslt-1.33
%P 287-293
Markdown (Informal)
[Data Augmentation by Concatenation for Low-Resource Translation: A Mystery and a Solution](https://aclanthology.org/2021.iwslt-1.33) (Nguyen et al., IWSLT 2021)
ACL