@inproceedings{moreno-etal-2024-awajun,
title = "Awajun-{OP}: Multi-domain dataset for {S}panish{--}Awajun Machine Translation",
author = "Moreno, Oscar and
Atamain, Yanua and
Oncevay, Arturo",
editor = "Mager, Manuel and
Ebrahimi, Abteen and
Rijhwani, Shruti and
Oncevay, Arturo and
Chiruzzo, Luis and
Pugh, Robert and
von der Wense, Katharina",
booktitle = "Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.americasnlp-1.12/",
doi = "10.18653/v1/2024.americasnlp-1.12",
pages = "112--120",
abstract = "We introduce a Spanish-Awajun parallel dataset of 22k high-quality sentence pairs with the help of the journalistic organization Company C. This dataset consists of parallel data obtained from various web sources such as poems, stories, laws, protocols, guidelines, handbooks, the Bible, and news published by Company C. The study also includes an analysis of the dataset`s performance for Spanish-Awajun translation using a Transformer architecture with transfer learning from a parent model, utilizing Spanish-English and Spanish-Finnish as high-resource language-pairs. As far as we know, this is the first Spanish-Awajun machine translation study, and we hope that this work will serve as a starting point for future research on this neglected Peruvian language."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moreno-etal-2024-awajun">
<titleInfo>
<title>Awajun-OP: Multi-domain dataset for Spanish–Awajun Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oscar</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanua</namePart>
<namePart type="family">Atamain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Oncevay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024)</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">Shruti</namePart>
<namePart type="family">Rijhwani</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">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Pugh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">von der Wense</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce a Spanish-Awajun parallel dataset of 22k high-quality sentence pairs with the help of the journalistic organization Company C. This dataset consists of parallel data obtained from various web sources such as poems, stories, laws, protocols, guidelines, handbooks, the Bible, and news published by Company C. The study also includes an analysis of the dataset‘s performance for Spanish-Awajun translation using a Transformer architecture with transfer learning from a parent model, utilizing Spanish-English and Spanish-Finnish as high-resource language-pairs. As far as we know, this is the first Spanish-Awajun machine translation study, and we hope that this work will serve as a starting point for future research on this neglected Peruvian language.</abstract>
<identifier type="citekey">moreno-etal-2024-awajun</identifier>
<identifier type="doi">10.18653/v1/2024.americasnlp-1.12</identifier>
<location>
<url>https://aclanthology.org/2024.americasnlp-1.12/</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>112</start>
<end>120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Awajun-OP: Multi-domain dataset for Spanish–Awajun Machine Translation
%A Moreno, Oscar
%A Atamain, Yanua
%A Oncevay, Arturo
%Y Mager, Manuel
%Y Ebrahimi, Abteen
%Y Rijhwani, Shruti
%Y Oncevay, Arturo
%Y Chiruzzo, Luis
%Y Pugh, Robert
%Y von der Wense, Katharina
%S Proceedings of the 4th Workshop on Natural Language Processing for Indigenous Languages of the Americas (AmericasNLP 2024)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F moreno-etal-2024-awajun
%X We introduce a Spanish-Awajun parallel dataset of 22k high-quality sentence pairs with the help of the journalistic organization Company C. This dataset consists of parallel data obtained from various web sources such as poems, stories, laws, protocols, guidelines, handbooks, the Bible, and news published by Company C. The study also includes an analysis of the dataset‘s performance for Spanish-Awajun translation using a Transformer architecture with transfer learning from a parent model, utilizing Spanish-English and Spanish-Finnish as high-resource language-pairs. As far as we know, this is the first Spanish-Awajun machine translation study, and we hope that this work will serve as a starting point for future research on this neglected Peruvian language.
%R 10.18653/v1/2024.americasnlp-1.12
%U https://aclanthology.org/2024.americasnlp-1.12/
%U https://doi.org/10.18653/v1/2024.americasnlp-1.12
%P 112-120
Markdown (Informal)
[Awajun-OP: Multi-domain dataset for Spanish–Awajun Machine Translation](https://aclanthology.org/2024.americasnlp-1.12/) (Moreno et al., AmericasNLP 2024)
ACL