@inproceedings{pendas-etal-2023-neural,
title = "Neural Machine Translation through Active Learning on low-resource languages: The case of {S}panish to {M}apudungun",
author = "Pendas, Bego{\~n}a and
Carvallo, Andres and
Aspillaga, Carlos",
editor = "Mager, Manuel and
Ebrahimi, Abteen and
Oncevay, Arturo and
Rice, Enora and
Rijhwani, Shruti and
Palmer, Alexis and
Kann, Katharina",
booktitle = "Proceedings of the Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.americasnlp-1.2",
doi = "10.18653/v1/2023.americasnlp-1.2",
pages = "6--11",
abstract = "Active learning is an algorithmic approach that strategically selects a subset of examples for labeling, with the goal of reducing workload and required resources. Previous research has applied active learning to Neural Machine Translation (NMT) for high-resource or well-represented languages, achieving significant reductions in manual labor. In this study, we explore the application of active learning for NMT in the context of Mapudungun, a low-resource language spoken by the Mapuche community in South America. Mapudungun was chosen due to the limited number of fluent speakers and the pressing need to provide access to content predominantly available in widely represented languages. We assess both model-dependent and model-agnostic active learning strategies for NMT between Spanish and Mapudungun in both directions, demonstrating that we can achieve over 40{\%} reduction in manual translation workload in both cases.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pendas-etal-2023-neural">
<titleInfo>
<title>Neural Machine Translation through Active Learning on low-resource languages: The case of Spanish to Mapudungun</title>
</titleInfo>
<name type="personal">
<namePart type="given">Begoña</namePart>
<namePart type="family">Pendas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andres</namePart>
<namePart type="family">Carvallo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Aspillaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="family">Mager</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abteen</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Oncevay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enora</namePart>
<namePart type="family">Rice</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Rijhwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">Kann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Active learning is an algorithmic approach that strategically selects a subset of examples for labeling, with the goal of reducing workload and required resources. Previous research has applied active learning to Neural Machine Translation (NMT) for high-resource or well-represented languages, achieving significant reductions in manual labor. In this study, we explore the application of active learning for NMT in the context of Mapudungun, a low-resource language spoken by the Mapuche community in South America. Mapudungun was chosen due to the limited number of fluent speakers and the pressing need to provide access to content predominantly available in widely represented languages. We assess both model-dependent and model-agnostic active learning strategies for NMT between Spanish and Mapudungun in both directions, demonstrating that we can achieve over 40% reduction in manual translation workload in both cases.</abstract>
<identifier type="citekey">pendas-etal-2023-neural</identifier>
<identifier type="doi">10.18653/v1/2023.americasnlp-1.2</identifier>
<location>
<url>https://aclanthology.org/2023.americasnlp-1.2</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>6</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Machine Translation through Active Learning on low-resource languages: The case of Spanish to Mapudungun
%A Pendas, Begoña
%A Carvallo, Andres
%A Aspillaga, Carlos
%Y Mager, Manuel
%Y Ebrahimi, Abteen
%Y Oncevay, Arturo
%Y Rice, Enora
%Y Rijhwani, Shruti
%Y Palmer, Alexis
%Y Kann, Katharina
%S Proceedings of the Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F pendas-etal-2023-neural
%X Active learning is an algorithmic approach that strategically selects a subset of examples for labeling, with the goal of reducing workload and required resources. Previous research has applied active learning to Neural Machine Translation (NMT) for high-resource or well-represented languages, achieving significant reductions in manual labor. In this study, we explore the application of active learning for NMT in the context of Mapudungun, a low-resource language spoken by the Mapuche community in South America. Mapudungun was chosen due to the limited number of fluent speakers and the pressing need to provide access to content predominantly available in widely represented languages. We assess both model-dependent and model-agnostic active learning strategies for NMT between Spanish and Mapudungun in both directions, demonstrating that we can achieve over 40% reduction in manual translation workload in both cases.
%R 10.18653/v1/2023.americasnlp-1.2
%U https://aclanthology.org/2023.americasnlp-1.2
%U https://doi.org/10.18653/v1/2023.americasnlp-1.2
%P 6-11
Markdown (Informal)
[Neural Machine Translation through Active Learning on low-resource languages: The case of Spanish to Mapudungun](https://aclanthology.org/2023.americasnlp-1.2) (Pendas et al., AmericasNLP 2023)
ACL