@inproceedings{cuadros-etal-2026-schema,
title = "Schema-Constrained Image Captioning for Five Low-Resource Indigenous Languages",
author = "Cuadros, Diego and
Leeds, Nicholas and
Avalos, Amanda and
Alpizar-Velazquez, Azul and
Coleman, Jared and
Dehghan Tarzjani, Faezeh and
Krishnamachari, Bhaskar",
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-6.24/",
pages = "257--263",
ISBN = "979-8-89176-415-6",
abstract = "We describe our submission to all five tracks of the AmericasNLP 2026 Shared Task on Cultural Image Captioning: Bribri, Guaran{\'i}, Yucatec Maya, Orizaba Nahuatl, and Wix{\'a}rika. Our system is an LLM-assisted rule-based machine translation (LLM-RBMT) captioner. For each language, a coding agent reads the small development split and open-web linguistic references and writes a complete Pydantic grammar package with a closed vocabulary. At inference time, a vision{--}language model sees the image and the schema, emits a structured SentenceList under constrained decoding, and a deterministic Python renderer produces the surface string. The model never generates target-language tokens. The same architecture handles all five languages with no fine-tuning, no parallel corpora, and no human edits to the generated packages. On the official test set, the system placed first on human evaluation in Bribri and Orizaba Nahuatl, third on Yucatec Maya, and first on ChrF++ in Yucatec Maya. We suggest that a strength of the approach is that outputs are restricted to simple sentences that are grammatically correct by construction, modulo the correctness of the generated grammar itself."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cuadros-etal-2026-schema">
<titleInfo>
<title>Schema-Constrained Image Captioning for Five Low-Resource Indigenous Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Cuadros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Leeds</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amanda</namePart>
<namePart type="family">Avalos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Azul</namePart>
<namePart type="family">Alpizar-Velazquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jared</namePart>
<namePart type="family">Coleman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Faezeh</namePart>
<namePart type="family">Dehghan Tarzjani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhaskar</namePart>
<namePart type="family">Krishnamachari</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 our submission to all five tracks of the AmericasNLP 2026 Shared Task on Cultural Image Captioning: Bribri, Guaraní, Yucatec Maya, Orizaba Nahuatl, and Wixárika. Our system is an LLM-assisted rule-based machine translation (LLM-RBMT) captioner. For each language, a coding agent reads the small development split and open-web linguistic references and writes a complete Pydantic grammar package with a closed vocabulary. At inference time, a vision–language model sees the image and the schema, emits a structured SentenceList under constrained decoding, and a deterministic Python renderer produces the surface string. The model never generates target-language tokens. The same architecture handles all five languages with no fine-tuning, no parallel corpora, and no human edits to the generated packages. On the official test set, the system placed first on human evaluation in Bribri and Orizaba Nahuatl, third on Yucatec Maya, and first on ChrF++ in Yucatec Maya. We suggest that a strength of the approach is that outputs are restricted to simple sentences that are grammatically correct by construction, modulo the correctness of the generated grammar itself.</abstract>
<identifier type="citekey">cuadros-etal-2026-schema</identifier>
<location>
<url>https://aclanthology.org/2026.americasnlp-6.24/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>257</start>
<end>263</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Schema-Constrained Image Captioning for Five Low-Resource Indigenous Languages
%A Cuadros, Diego
%A Leeds, Nicholas
%A Avalos, Amanda
%A Alpizar-Velazquez, Azul
%A Coleman, Jared
%A Dehghan Tarzjani, Faezeh
%A Krishnamachari, Bhaskar
%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 cuadros-etal-2026-schema
%X We describe our submission to all five tracks of the AmericasNLP 2026 Shared Task on Cultural Image Captioning: Bribri, Guaraní, Yucatec Maya, Orizaba Nahuatl, and Wixárika. Our system is an LLM-assisted rule-based machine translation (LLM-RBMT) captioner. For each language, a coding agent reads the small development split and open-web linguistic references and writes a complete Pydantic grammar package with a closed vocabulary. At inference time, a vision–language model sees the image and the schema, emits a structured SentenceList under constrained decoding, and a deterministic Python renderer produces the surface string. The model never generates target-language tokens. The same architecture handles all five languages with no fine-tuning, no parallel corpora, and no human edits to the generated packages. On the official test set, the system placed first on human evaluation in Bribri and Orizaba Nahuatl, third on Yucatec Maya, and first on ChrF++ in Yucatec Maya. We suggest that a strength of the approach is that outputs are restricted to simple sentences that are grammatically correct by construction, modulo the correctness of the generated grammar itself.
%U https://aclanthology.org/2026.americasnlp-6.24/
%P 257-263
Markdown (Informal)
[Schema-Constrained Image Captioning for Five Low-Resource Indigenous Languages](https://aclanthology.org/2026.americasnlp-6.24/) (Cuadros et al., AmericasNLP 2026)
ACL
- Diego Cuadros, Nicholas Leeds, Amanda Avalos, Azul Alpizar-Velazquez, Jared Coleman, Faezeh Dehghan Tarzjani, and Bhaskar Krishnamachari. 2026. Schema-Constrained Image Captioning for Five Low-Resource Indigenous Languages. In Proceedings of the Sixth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP), pages 257–263, San Diego, California, USA. Association for Computational Linguistics.