@inproceedings{degenaro-lupicki-2024-experiments,
title = "Experiments in Mamba Sequence Modeling and {NLLB}-200 Fine-Tuning for Low Resource Multilingual Machine Translation",
author = "Degenaro, Dan and
Lupicki, Tom",
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-1.22",
doi = "10.18653/v1/2024.americasnlp-1.22",
pages = "188--194",
abstract = "This paper presents DC{\_}DMV{'}s submission to the AmericasNLP 2024 Shared Task 1: Machine Translation Systems for Indigenous Languages. Our submission consists of two multilingual approaches to building machine translation systems from Spanish to eleven Indigenous languages: fine-tuning the 600M distilled variant of NLLB-200, and an experiment in training from scratch a neural network using the Mamba State Space Modeling architecture. We achieve the best results on the test set for a total of 4 of the language pairs between two checkpoints by fine-tuning NLLB-200, and outperform the baseline score on the test set for 2 languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="degenaro-lupicki-2024-experiments">
<titleInfo>
<title>Experiments in Mamba Sequence Modeling and NLLB-200 Fine-Tuning for Low Resource Multilingual Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Degenaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tom</namePart>
<namePart type="family">Lupicki</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>This paper presents DC_DMV’s submission to the AmericasNLP 2024 Shared Task 1: Machine Translation Systems for Indigenous Languages. Our submission consists of two multilingual approaches to building machine translation systems from Spanish to eleven Indigenous languages: fine-tuning the 600M distilled variant of NLLB-200, and an experiment in training from scratch a neural network using the Mamba State Space Modeling architecture. We achieve the best results on the test set for a total of 4 of the language pairs between two checkpoints by fine-tuning NLLB-200, and outperform the baseline score on the test set for 2 languages.</abstract>
<identifier type="citekey">degenaro-lupicki-2024-experiments</identifier>
<identifier type="doi">10.18653/v1/2024.americasnlp-1.22</identifier>
<location>
<url>https://aclanthology.org/2024.americasnlp-1.22</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>188</start>
<end>194</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Experiments in Mamba Sequence Modeling and NLLB-200 Fine-Tuning for Low Resource Multilingual Machine Translation
%A Degenaro, Dan
%A Lupicki, Tom
%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 degenaro-lupicki-2024-experiments
%X This paper presents DC_DMV’s submission to the AmericasNLP 2024 Shared Task 1: Machine Translation Systems for Indigenous Languages. Our submission consists of two multilingual approaches to building machine translation systems from Spanish to eleven Indigenous languages: fine-tuning the 600M distilled variant of NLLB-200, and an experiment in training from scratch a neural network using the Mamba State Space Modeling architecture. We achieve the best results on the test set for a total of 4 of the language pairs between two checkpoints by fine-tuning NLLB-200, and outperform the baseline score on the test set for 2 languages.
%R 10.18653/v1/2024.americasnlp-1.22
%U https://aclanthology.org/2024.americasnlp-1.22
%U https://doi.org/10.18653/v1/2024.americasnlp-1.22
%P 188-194
Markdown (Informal)
[Experiments in Mamba Sequence Modeling and NLLB-200 Fine-Tuning for Low Resource Multilingual Machine Translation](https://aclanthology.org/2024.americasnlp-1.22) (Degenaro & Lupicki, AmericasNLP-WS 2024)
ACL