@inproceedings{lamar-kaya-2023-measuring,
title = "Measuring the Impact of Data Augmentation Methods for Extremely Low-Resource {NMT}",
author = "Lamar, Annie and
Kaya, Zeyneb",
editor = "Ojha, Atul Kr. and
Liu, Chao-hong and
Vylomova, Ekaterina and
Pirinen, Flammie and
Abbott, Jade and
Washington, Jonathan and
Oco, Nathaniel and
Malykh, Valentin and
Logacheva, Varvara and
Zhao, Xiaobing",
booktitle = "Proceedings of the Sixth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2023)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.loresmt-1.8",
doi = "10.18653/v1/2023.loresmt-1.8",
pages = "101--109",
abstract = "Data augmentation (DA) is a popular strategy to boost performance on neural machine translation tasks. The impact of data augmentation in low-resource environments, particularly for diverse and scarce languages, is understudied. In this paper, we introduce a simple yet novel metric to measure the impact of several different data augmentation strategies. This metric, which we call Data Augmentation Advantage (DAA), quantifies how many true data pairs a synthetic data pair is worth in a particular experimental context. We demonstrate the utility of this metric by training models for several linguistically-varied datasets using the data augmentation methods of back-translation, SwitchOut, and sentence concatenation. In lower-resource tasks, DAA is an especially valuable metric for comparing DA performance as it provides a more effective way to quantify gains when BLEU scores are especially small and results across diverse languages are more divergent and difficult to assess.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lamar-kaya-2023-measuring">
<titleInfo>
<title>Measuring the Impact of Data Augmentation Methods for Extremely Low-Resource NMT</title>
</titleInfo>
<name type="personal">
<namePart type="given">Annie</namePart>
<namePart type="family">Lamar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeyneb</namePart>
<namePart type="family">Kaya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao-hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jade</namePart>
<namePart type="family">Abbott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Washington</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Oco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varvara</namePart>
<namePart type="family">Logacheva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaobing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data augmentation (DA) is a popular strategy to boost performance on neural machine translation tasks. The impact of data augmentation in low-resource environments, particularly for diverse and scarce languages, is understudied. In this paper, we introduce a simple yet novel metric to measure the impact of several different data augmentation strategies. This metric, which we call Data Augmentation Advantage (DAA), quantifies how many true data pairs a synthetic data pair is worth in a particular experimental context. We demonstrate the utility of this metric by training models for several linguistically-varied datasets using the data augmentation methods of back-translation, SwitchOut, and sentence concatenation. In lower-resource tasks, DAA is an especially valuable metric for comparing DA performance as it provides a more effective way to quantify gains when BLEU scores are especially small and results across diverse languages are more divergent and difficult to assess.</abstract>
<identifier type="citekey">lamar-kaya-2023-measuring</identifier>
<identifier type="doi">10.18653/v1/2023.loresmt-1.8</identifier>
<location>
<url>https://aclanthology.org/2023.loresmt-1.8</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>101</start>
<end>109</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Measuring the Impact of Data Augmentation Methods for Extremely Low-Resource NMT
%A Lamar, Annie
%A Kaya, Zeyneb
%Y Ojha, Atul Kr.
%Y Liu, Chao-hong
%Y Vylomova, Ekaterina
%Y Pirinen, Flammie
%Y Abbott, Jade
%Y Washington, Jonathan
%Y Oco, Nathaniel
%Y Malykh, Valentin
%Y Logacheva, Varvara
%Y Zhao, Xiaobing
%S Proceedings of the Sixth Workshop on Technologies for Machine Translation of Low-Resource Languages (LoResMT 2023)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F lamar-kaya-2023-measuring
%X Data augmentation (DA) is a popular strategy to boost performance on neural machine translation tasks. The impact of data augmentation in low-resource environments, particularly for diverse and scarce languages, is understudied. In this paper, we introduce a simple yet novel metric to measure the impact of several different data augmentation strategies. This metric, which we call Data Augmentation Advantage (DAA), quantifies how many true data pairs a synthetic data pair is worth in a particular experimental context. We demonstrate the utility of this metric by training models for several linguistically-varied datasets using the data augmentation methods of back-translation, SwitchOut, and sentence concatenation. In lower-resource tasks, DAA is an especially valuable metric for comparing DA performance as it provides a more effective way to quantify gains when BLEU scores are especially small and results across diverse languages are more divergent and difficult to assess.
%R 10.18653/v1/2023.loresmt-1.8
%U https://aclanthology.org/2023.loresmt-1.8
%U https://doi.org/10.18653/v1/2023.loresmt-1.8
%P 101-109
Markdown (Informal)
[Measuring the Impact of Data Augmentation Methods for Extremely Low-Resource NMT](https://aclanthology.org/2023.loresmt-1.8) (Lamar & Kaya, LoResMT 2023)
ACL