@inproceedings{dhawan-etal-2026-retrieval,
title = "Retrieval-Augmented Long-Context Translation for Cultural Image Captioning: Gators submission for {A}mericas{NLP} 2026 shared task",
author = "Dhawan, Aashish and
Driggers-Ellis, Christopher and
Kasinets, Dzmitry and
Grant, Christan and
Wang, Zhe",
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-6.19/",
pages = "212--223",
ISBN = "979-8-89176-415-6",
abstract = "This paper presents the University of Florida Gators submission to the AmericasNLP 2026 shared task on cultural image captioning for Indigenous languages. The system uses a two-stage pipeline: first generating Spanish captions from images with a vision-language model, then translating them into target languages using retrieval-augmented many-shot prompting with Gemini 2.5 Flash. The paper reports strong improvements over the shared task baseline across multiple languages, analyzes the role of retrieval, synthetic exemplars, and morphology-aware prompting, and discusses limitations related to dev-set exemplars, cascade errors, and chrF++ based evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dhawan-etal-2026-retrieval">
<titleInfo>
<title>Retrieval-Augmented Long-Context Translation for Cultural Image Captioning: Gators submission for AmericasNLP 2026 shared task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aashish</namePart>
<namePart type="family">Dhawan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Driggers-Ellis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dzmitry</namePart>
<namePart type="family">Kasinets</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christan</namePart>
<namePart type="family">Grant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhe</namePart>
<namePart type="family">Wang</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>This paper presents the University of Florida Gators submission to the AmericasNLP 2026 shared task on cultural image captioning for Indigenous languages. The system uses a two-stage pipeline: first generating Spanish captions from images with a vision-language model, then translating them into target languages using retrieval-augmented many-shot prompting with Gemini 2.5 Flash. The paper reports strong improvements over the shared task baseline across multiple languages, analyzes the role of retrieval, synthetic exemplars, and morphology-aware prompting, and discusses limitations related to dev-set exemplars, cascade errors, and chrF++ based evaluation.</abstract>
<identifier type="citekey">dhawan-etal-2026-retrieval</identifier>
<location>
<url>https://aclanthology.org/2026.americasnlp-6.19/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>212</start>
<end>223</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Retrieval-Augmented Long-Context Translation for Cultural Image Captioning: Gators submission for AmericasNLP 2026 shared task
%A Dhawan, Aashish
%A Driggers-Ellis, Christopher
%A Kasinets, Dzmitry
%A Grant, Christan
%A Wang, Zhe
%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 dhawan-etal-2026-retrieval
%X This paper presents the University of Florida Gators submission to the AmericasNLP 2026 shared task on cultural image captioning for Indigenous languages. The system uses a two-stage pipeline: first generating Spanish captions from images with a vision-language model, then translating them into target languages using retrieval-augmented many-shot prompting with Gemini 2.5 Flash. The paper reports strong improvements over the shared task baseline across multiple languages, analyzes the role of retrieval, synthetic exemplars, and morphology-aware prompting, and discusses limitations related to dev-set exemplars, cascade errors, and chrF++ based evaluation.
%U https://aclanthology.org/2026.americasnlp-6.19/
%P 212-223
Markdown (Informal)
[Retrieval-Augmented Long-Context Translation for Cultural Image Captioning: Gators submission for AmericasNLP 2026 shared task](https://aclanthology.org/2026.americasnlp-6.19/) (Dhawan et al., AmericasNLP 2026)
ACL