@inproceedings{krasner-etal-2025-machine,
title = "Machine Translation Metrics for Indigenous Languages Using Fine-tuned Semantic Embeddings",
author = "Krasner, Nathaniel and
Vasselli, Justin and
Ticona, Belu and
Anastasopoulos, Antonios and
Lo, Chi-Kiu",
editor = "Mager, Manuel and
Ebrahimi, Abteen and
Pugh, Robert and
Rijhwani, Shruti and
Von Der Wense, Katharina and
Chiruzzo, Luis and
Coto-Solano, Rolando and
Oncevay, Arturo",
booktitle = "Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)",
month = may,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.americasnlp-1.11/",
doi = "10.18653/v1/2025.americasnlp-1.11",
pages = "100--104",
ISBN = "979-8-89176-236-7",
abstract = "This paper describes the Tekio submission to the AmericasNLP 2025 shared task on machine translation metrics for Indigenous languages. We developed two primary metric approaches leveraging multilingual semantic embeddings. First, we fine-tuned the Language-agnostic BERT Sentence Encoder (LaBSE) specifically for Guarani, Bribri, and Nahuatl, significantly enhancing semantic representation quality. Next, we integrated our fine-tuned LaBSE into the semantic similarity metric YiSi-1, exploring the effectiveness of averaging multiple layers. Additionally, we trained regression-based COMET metrics (COMET-DA) using the fine-tuned LaBSE embeddings as a semantic backbone, comparing Mean Absolute Error (MAE) and Mean Squared Error (MSE) loss functions. Our YiSi-1 metric using layer-averaged embeddings chosen by having the best performance on the development set for each individual language achieved the highest average correlation across languages among our submitted systems, and our COMET models demonstrated competitive performance for Guarani."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krasner-etal-2025-machine">
<titleInfo>
<title>Machine Translation Metrics for Indigenous Languages Using Fine-tuned Semantic Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Krasner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Justin</namePart>
<namePart type="family">Vasselli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Belu</namePart>
<namePart type="family">Ticona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chi-Kiu</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on NLP 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">Robert</namePart>
<namePart type="family">Pugh</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">Katharina</namePart>
<namePart type="family">Von Der Wense</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">Rolando</namePart>
<namePart type="family">Coto-Solano</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-236-7</identifier>
</relatedItem>
<abstract>This paper describes the Tekio submission to the AmericasNLP 2025 shared task on machine translation metrics for Indigenous languages. We developed two primary metric approaches leveraging multilingual semantic embeddings. First, we fine-tuned the Language-agnostic BERT Sentence Encoder (LaBSE) specifically for Guarani, Bribri, and Nahuatl, significantly enhancing semantic representation quality. Next, we integrated our fine-tuned LaBSE into the semantic similarity metric YiSi-1, exploring the effectiveness of averaging multiple layers. Additionally, we trained regression-based COMET metrics (COMET-DA) using the fine-tuned LaBSE embeddings as a semantic backbone, comparing Mean Absolute Error (MAE) and Mean Squared Error (MSE) loss functions. Our YiSi-1 metric using layer-averaged embeddings chosen by having the best performance on the development set for each individual language achieved the highest average correlation across languages among our submitted systems, and our COMET models demonstrated competitive performance for Guarani.</abstract>
<identifier type="citekey">krasner-etal-2025-machine</identifier>
<identifier type="doi">10.18653/v1/2025.americasnlp-1.11</identifier>
<location>
<url>https://aclanthology.org/2025.americasnlp-1.11/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>100</start>
<end>104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Machine Translation Metrics for Indigenous Languages Using Fine-tuned Semantic Embeddings
%A Krasner, Nathaniel
%A Vasselli, Justin
%A Ticona, Belu
%A Anastasopoulos, Antonios
%A Lo, Chi-Kiu
%Y Mager, Manuel
%Y Ebrahimi, Abteen
%Y Pugh, Robert
%Y Rijhwani, Shruti
%Y Von Der Wense, Katharina
%Y Chiruzzo, Luis
%Y Coto-Solano, Rolando
%Y Oncevay, Arturo
%S Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-236-7
%F krasner-etal-2025-machine
%X This paper describes the Tekio submission to the AmericasNLP 2025 shared task on machine translation metrics for Indigenous languages. We developed two primary metric approaches leveraging multilingual semantic embeddings. First, we fine-tuned the Language-agnostic BERT Sentence Encoder (LaBSE) specifically for Guarani, Bribri, and Nahuatl, significantly enhancing semantic representation quality. Next, we integrated our fine-tuned LaBSE into the semantic similarity metric YiSi-1, exploring the effectiveness of averaging multiple layers. Additionally, we trained regression-based COMET metrics (COMET-DA) using the fine-tuned LaBSE embeddings as a semantic backbone, comparing Mean Absolute Error (MAE) and Mean Squared Error (MSE) loss functions. Our YiSi-1 metric using layer-averaged embeddings chosen by having the best performance on the development set for each individual language achieved the highest average correlation across languages among our submitted systems, and our COMET models demonstrated competitive performance for Guarani.
%R 10.18653/v1/2025.americasnlp-1.11
%U https://aclanthology.org/2025.americasnlp-1.11/
%U https://doi.org/10.18653/v1/2025.americasnlp-1.11
%P 100-104
Markdown (Informal)
[Machine Translation Metrics for Indigenous Languages Using Fine-tuned Semantic Embeddings](https://aclanthology.org/2025.americasnlp-1.11/) (Krasner et al., AmericasNLP 2025)
ACL