@inproceedings{tonja-etal-2023-enhancing,
title = "Enhancing Translation for Indigenous Languages: Experiments with Multilingual Models",
author = "Tonja, Atnafu Lambebo and
Nigatu, Hellina Hailu and
Kolesnikova, Olga and
Sidorov, Grigori and
Gelbukh, Alexander and
Kalita, Jugal",
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-1.22",
doi = "10.18653/v1/2023.americasnlp-1.22",
pages = "200--205",
abstract = "This paper describes CIC NLP{'}s submission to the AmericasNLP 2023 Shared Task on machine translation systems for indigenous languages of the Americas. We present the system descriptions for three methods. We used two multilingual models, namely M2M-100 and mBART50, and one bilingual (one-to-one) {---} Helsinki NLP Spanish-English translation model, and experimented with different transfer learning setups. We experimented with 11 languages from America and report the setups we used as well as the results we achieved. Overall, the mBART setup was able to improve upon the baseline for three out of the eleven languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tonja-etal-2023-enhancing">
<titleInfo>
<title>Enhancing Translation for Indigenous Languages: Experiments with Multilingual Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atnafu</namePart>
<namePart type="given">Lambebo</namePart>
<namePart type="family">Tonja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hellina</namePart>
<namePart type="given">Hailu</namePart>
<namePart type="family">Nigatu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Kolesnikova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grigori</namePart>
<namePart type="family">Sidorov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Gelbukh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jugal</namePart>
<namePart type="family">Kalita</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>This paper describes CIC NLP’s submission to the AmericasNLP 2023 Shared Task on machine translation systems for indigenous languages of the Americas. We present the system descriptions for three methods. We used two multilingual models, namely M2M-100 and mBART50, and one bilingual (one-to-one) — Helsinki NLP Spanish-English translation model, and experimented with different transfer learning setups. We experimented with 11 languages from America and report the setups we used as well as the results we achieved. Overall, the mBART setup was able to improve upon the baseline for three out of the eleven languages.</abstract>
<identifier type="citekey">tonja-etal-2023-enhancing</identifier>
<identifier type="doi">10.18653/v1/2023.americasnlp-1.22</identifier>
<location>
<url>https://aclanthology.org/2023.americasnlp-1.22</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>200</start>
<end>205</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhancing Translation for Indigenous Languages: Experiments with Multilingual Models
%A Tonja, Atnafu Lambebo
%A Nigatu, Hellina Hailu
%A Kolesnikova, Olga
%A Sidorov, Grigori
%A Gelbukh, Alexander
%A Kalita, Jugal
%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 tonja-etal-2023-enhancing
%X This paper describes CIC NLP’s submission to the AmericasNLP 2023 Shared Task on machine translation systems for indigenous languages of the Americas. We present the system descriptions for three methods. We used two multilingual models, namely M2M-100 and mBART50, and one bilingual (one-to-one) — Helsinki NLP Spanish-English translation model, and experimented with different transfer learning setups. We experimented with 11 languages from America and report the setups we used as well as the results we achieved. Overall, the mBART setup was able to improve upon the baseline for three out of the eleven languages.
%R 10.18653/v1/2023.americasnlp-1.22
%U https://aclanthology.org/2023.americasnlp-1.22
%U https://doi.org/10.18653/v1/2023.americasnlp-1.22
%P 200-205
Markdown (Informal)
[Enhancing Translation for Indigenous Languages: Experiments with Multilingual Models](https://aclanthology.org/2023.americasnlp-1.22) (Tonja et al., AmericasNLP 2023)
ACL