@inproceedings{fernandes-2026-usp,
title = "{USP} at {A}mericas{NLP} 2026 Shared Task: Culturally-Aware Image Captioning for Indigenous Languages via Vision-Language Models and Fine-Tuned Neural Machine Translation",
author = "Fernandes, Rafael",
editor = "Mager, Manuel and
Ebrahimi, Abteen and
Bui, Minh Duc and
Pugh, Robert and
Oncevay, Arturo and
Chiruzzo, Luis and
Solano, Rolando Coto and
Rijhwani, Shruti and
Von Der Wense, Katharina",
booktitle = "Proceedings of the Sixth Workshop on {NLP} for Indigenous Languages of the {A}mericas ({A}mericas{NLP})",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.americasnlp-6.25/",
pages = "264--271",
ISBN = "979-8-89176-415-6",
abstract = "We describe the USP system for the AmericasNLP 2026 Shared Task on Culturally Relevant Image Captioning for Indigenous Languages, covering Guaran{\'i} (grn), Maya Yucateco (yua), Nahuatl (nah), Wix{\'a}rika (hch), and Bribri (bzd). We propose a two-stage cascade: Qwen3-VL-8B-Instruct (Bai et al., 2025) generates Spanish captions via language-specific cultural prompts; language-specific fine-tuned NLLB-200-distilled-600M (NLLB Team et al., 2022) models then translate them into each target language. We train on AmericasNLP 2023 data (Ebrahimi et al., 2023) augmented with public parallel corpora. Our system achieves competitive results, including 3rd place in Guaran{\'i} human evaluation (2.41/5.0) and 5th in Bribri (1.09/5.0) among 8 teams. We also report that NLLB-200-distilled-600M silently lacks vocabulary entries for Bribri and Maya Yucateco, producing English output without error."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fernandes-2026-usp">
<titleInfo>
<title>USP at AmericasNLP 2026 Shared Task: Culturally-Aware Image Captioning for Indigenous Languages via Vision-Language Models and Fine-Tuned Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Fernandes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth 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">Minh</namePart>
<namePart type="given">Duc</namePart>
<namePart type="family">Bui</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">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">Rolando</namePart>
<namePart type="given">Coto</namePart>
<namePart type="family">Solano</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-415-6</identifier>
</relatedItem>
<abstract>We describe the USP system for the AmericasNLP 2026 Shared Task on Culturally Relevant Image Captioning for Indigenous Languages, covering Guaraní (grn), Maya Yucateco (yua), Nahuatl (nah), Wixárika (hch), and Bribri (bzd). We propose a two-stage cascade: Qwen3-VL-8B-Instruct (Bai et al., 2025) generates Spanish captions via language-specific cultural prompts; language-specific fine-tuned NLLB-200-distilled-600M (NLLB Team et al., 2022) models then translate them into each target language. We train on AmericasNLP 2023 data (Ebrahimi et al., 2023) augmented with public parallel corpora. Our system achieves competitive results, including 3rd place in Guaraní human evaluation (2.41/5.0) and 5th in Bribri (1.09/5.0) among 8 teams. We also report that NLLB-200-distilled-600M silently lacks vocabulary entries for Bribri and Maya Yucateco, producing English output without error.</abstract>
<identifier type="citekey">fernandes-2026-usp</identifier>
<location>
<url>https://aclanthology.org/2026.americasnlp-6.25/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>264</start>
<end>271</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T USP at AmericasNLP 2026 Shared Task: Culturally-Aware Image Captioning for Indigenous Languages via Vision-Language Models and Fine-Tuned Neural Machine Translation
%A Fernandes, Rafael
%Y Mager, Manuel
%Y Ebrahimi, Abteen
%Y Bui, Minh Duc
%Y Pugh, Robert
%Y Oncevay, Arturo
%Y Chiruzzo, Luis
%Y Solano, Rolando Coto
%Y Rijhwani, Shruti
%Y Von Der Wense, Katharina
%S Proceedings of the Sixth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-415-6
%F fernandes-2026-usp
%X We describe the USP system for the AmericasNLP 2026 Shared Task on Culturally Relevant Image Captioning for Indigenous Languages, covering Guaraní (grn), Maya Yucateco (yua), Nahuatl (nah), Wixárika (hch), and Bribri (bzd). We propose a two-stage cascade: Qwen3-VL-8B-Instruct (Bai et al., 2025) generates Spanish captions via language-specific cultural prompts; language-specific fine-tuned NLLB-200-distilled-600M (NLLB Team et al., 2022) models then translate them into each target language. We train on AmericasNLP 2023 data (Ebrahimi et al., 2023) augmented with public parallel corpora. Our system achieves competitive results, including 3rd place in Guaraní human evaluation (2.41/5.0) and 5th in Bribri (1.09/5.0) among 8 teams. We also report that NLLB-200-distilled-600M silently lacks vocabulary entries for Bribri and Maya Yucateco, producing English output without error.
%U https://aclanthology.org/2026.americasnlp-6.25/
%P 264-271
Markdown (Informal)
[USP at AmericasNLP 2026 Shared Task: Culturally-Aware Image Captioning for Indigenous Languages via Vision-Language Models and Fine-Tuned Neural Machine Translation](https://aclanthology.org/2026.americasnlp-6.25/) (Fernandes, AmericasNLP 2026)
ACL