@inproceedings{de-gibert-etal-2023-four,
title = "Four Approaches to Low-Resource Multilingual {NMT}: The {H}elsinki Submission to the {A}mericas{NLP} 2023 Shared Task",
author = {De Gibert, Ona and
V{\'a}zquez, Ra{\'u}l and
Aulamo, Mikko and
Scherrer, Yves and
Virpioja, Sami and
Tiedemann, J{\"o}rg},
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-1.20",
doi = "10.18653/v1/2023.americasnlp-1.20",
pages = "177--191",
abstract = "The Helsinki-NLP team participated in the AmericasNLP 2023 Shared Task with 6 submissions for all 11 language pairs arising from 4 different multilingual systems. We provide a detailed look at the work that went into collecting and preprocessing the data that led to our submissions. We explore various setups for multilingual Neural Machine Translation (NMT), namely knowledge distillation and transfer learning, multilingual NMT including a high-resource language (English), language-specific fine-tuning, and multilingual NMT exclusively using low-resource data. Our multilingual Model B ranks first in 4 out of the 11 language pairs.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="de-gibert-etal-2023-four">
<titleInfo>
<title>Four Approaches to Low-Resource Multilingual NMT: The Helsinki Submission to the AmericasNLP 2023 Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ona</namePart>
<namePart type="family">De Gibert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="family">Vázquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikko</namePart>
<namePart type="family">Aulamo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Scherrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sami</namePart>
<namePart type="family">Virpioja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</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>The Helsinki-NLP team participated in the AmericasNLP 2023 Shared Task with 6 submissions for all 11 language pairs arising from 4 different multilingual systems. We provide a detailed look at the work that went into collecting and preprocessing the data that led to our submissions. We explore various setups for multilingual Neural Machine Translation (NMT), namely knowledge distillation and transfer learning, multilingual NMT including a high-resource language (English), language-specific fine-tuning, and multilingual NMT exclusively using low-resource data. Our multilingual Model B ranks first in 4 out of the 11 language pairs.</abstract>
<identifier type="citekey">de-gibert-etal-2023-four</identifier>
<identifier type="doi">10.18653/v1/2023.americasnlp-1.20</identifier>
<location>
<url>https://aclanthology.org/2023.americasnlp-1.20</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>177</start>
<end>191</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Four Approaches to Low-Resource Multilingual NMT: The Helsinki Submission to the AmericasNLP 2023 Shared Task
%A De Gibert, Ona
%A Vázquez, Raúl
%A Aulamo, Mikko
%A Scherrer, Yves
%A Virpioja, Sami
%A Tiedemann, Jörg
%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 de-gibert-etal-2023-four
%X The Helsinki-NLP team participated in the AmericasNLP 2023 Shared Task with 6 submissions for all 11 language pairs arising from 4 different multilingual systems. We provide a detailed look at the work that went into collecting and preprocessing the data that led to our submissions. We explore various setups for multilingual Neural Machine Translation (NMT), namely knowledge distillation and transfer learning, multilingual NMT including a high-resource language (English), language-specific fine-tuning, and multilingual NMT exclusively using low-resource data. Our multilingual Model B ranks first in 4 out of the 11 language pairs.
%R 10.18653/v1/2023.americasnlp-1.20
%U https://aclanthology.org/2023.americasnlp-1.20
%U https://doi.org/10.18653/v1/2023.americasnlp-1.20
%P 177-191
Markdown (Informal)
[Four Approaches to Low-Resource Multilingual NMT: The Helsinki Submission to the AmericasNLP 2023 Shared Task](https://aclanthology.org/2023.americasnlp-1.20) (De Gibert et al., AmericasNLP 2023)
ACL