@inproceedings{bui-von-der-wense-2024-jgu,
title = "{JGU} Mainz{'}s Submission to the {A}mericas{NLP} 2024 Shared Task on the Creation of Educational Materials for Indigenous Languages",
author = "Bui, Minh Duc and
von der Wense, Katharina",
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-1.23",
pages = "195--200",
abstract = "In this paper, we present the four systems developed by the Meenzer team from JGU for the AmericasNLP 2024 shared task on the creation of educational materials for Indigenous languages. The task involves accurately applying specific grammatical modifications to given source sentences across three low-resource Indigenous languages: Bribri, Guarani, and Maya. We train two types of model architectures: finetuning a sequence-to-sequence pointer-generator LSTM and finetuning the Mixtral 8x7B model by incorporating in-context examples into the training phase. System 1, an ensemble combining finetuned LSTMs, finetuned Mixtral models, and GPT-4, achieves the best performance on Guarani. Meanwhile, system 4, another ensemble consisting solely of fine-tuned Mixtral models, outperforms all other teams on Maya and secures the second place overall. Additionally, we conduct an ablation study to understand the performance of our system 4.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bui-von-der-wense-2024-jgu">
<titleInfo>
<title>JGU Mainz’s Submission to the AmericasNLP 2024 Shared Task on the Creation of Educational Materials for Indigenous Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minh</namePart>
<namePart type="given">Duc</namePart>
<namePart type="family">Bui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katharina</namePart>
<namePart type="family">von der Wense</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>In this paper, we present the four systems developed by the Meenzer team from JGU for the AmericasNLP 2024 shared task on the creation of educational materials for Indigenous languages. The task involves accurately applying specific grammatical modifications to given source sentences across three low-resource Indigenous languages: Bribri, Guarani, and Maya. We train two types of model architectures: finetuning a sequence-to-sequence pointer-generator LSTM and finetuning the Mixtral 8x7B model by incorporating in-context examples into the training phase. System 1, an ensemble combining finetuned LSTMs, finetuned Mixtral models, and GPT-4, achieves the best performance on Guarani. Meanwhile, system 4, another ensemble consisting solely of fine-tuned Mixtral models, outperforms all other teams on Maya and secures the second place overall. Additionally, we conduct an ablation study to understand the performance of our system 4.</abstract>
<identifier type="citekey">bui-von-der-wense-2024-jgu</identifier>
<location>
<url>https://aclanthology.org/2024.americasnlp-1.23</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>195</start>
<end>200</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T JGU Mainz’s Submission to the AmericasNLP 2024 Shared Task on the Creation of Educational Materials for Indigenous Languages
%A Bui, Minh Duc
%A von der Wense, Katharina
%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 bui-von-der-wense-2024-jgu
%X In this paper, we present the four systems developed by the Meenzer team from JGU for the AmericasNLP 2024 shared task on the creation of educational materials for Indigenous languages. The task involves accurately applying specific grammatical modifications to given source sentences across three low-resource Indigenous languages: Bribri, Guarani, and Maya. We train two types of model architectures: finetuning a sequence-to-sequence pointer-generator LSTM and finetuning the Mixtral 8x7B model by incorporating in-context examples into the training phase. System 1, an ensemble combining finetuned LSTMs, finetuned Mixtral models, and GPT-4, achieves the best performance on Guarani. Meanwhile, system 4, another ensemble consisting solely of fine-tuned Mixtral models, outperforms all other teams on Maya and secures the second place overall. Additionally, we conduct an ablation study to understand the performance of our system 4.
%U https://aclanthology.org/2024.americasnlp-1.23
%P 195-200
Markdown (Informal)
[JGU Mainz’s Submission to the AmericasNLP 2024 Shared Task on the Creation of Educational Materials for Indigenous Languages](https://aclanthology.org/2024.americasnlp-1.23) (Bui & von der Wense, AmericasNLP-WS 2024)
ACL