@inproceedings{umeres-cabezudo-2026-pictoeduca,
title = "{P}icto{E}duca: Building a Dataset for {S}panish Text-to-Pictogram Generation",
author = "Umeres, Alfonso Manuel Paredes and
Cabezudo, Marco Antonio Sobrevilla",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1738/",
doi = "10.18653/v1/2026.findings-acl.1738",
pages = "34816--34828",
ISBN = "979-8-89176-395-1",
abstract = "We present PictoEduca, the first large-scale Spanish text-to-pictogram dataset for augmentative and alternative communication (AAC), derived from primary educational materials and grounded in the ARASAAC pictogram repository. The dataset is released with a reproducible pipeline that combines automatic annotation with targeted expert correction, supporting scalable and high-quality corpus construction. We benchmark a rule-based system (ARAWORD) and neural models (T5, LLaMA) under direct text-to-pictogram and two-stage text-to-concept-to-pictogram settings. Results show that the rule-based system remains a strong baseline, while neural models benefit from explicit semantic abstraction, with the two-stage approach improving semantic coherence and reducing ambiguity. We further explore data selection strategies, demonstrating that combining domain similarity with a quality signal yields higher-quality silver data, reduces annotation effort, and improves model performance in low-resource regimes. PictoEduca enables reproducible evaluation and advances Spanish text-to-pictogram research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="umeres-cabezudo-2026-pictoeduca">
<titleInfo>
<title>PictoEduca: Building a Dataset for Spanish Text-to-Pictogram Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alfonso</namePart>
<namePart type="given">Manuel</namePart>
<namePart type="given">Paredes</namePart>
<namePart type="family">Umeres</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="given">Antonio</namePart>
<namePart type="given">Sobrevilla</namePart>
<namePart type="family">Cabezudo</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>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</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, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>We present PictoEduca, the first large-scale Spanish text-to-pictogram dataset for augmentative and alternative communication (AAC), derived from primary educational materials and grounded in the ARASAAC pictogram repository. The dataset is released with a reproducible pipeline that combines automatic annotation with targeted expert correction, supporting scalable and high-quality corpus construction. We benchmark a rule-based system (ARAWORD) and neural models (T5, LLaMA) under direct text-to-pictogram and two-stage text-to-concept-to-pictogram settings. Results show that the rule-based system remains a strong baseline, while neural models benefit from explicit semantic abstraction, with the two-stage approach improving semantic coherence and reducing ambiguity. We further explore data selection strategies, demonstrating that combining domain similarity with a quality signal yields higher-quality silver data, reduces annotation effort, and improves model performance in low-resource regimes. PictoEduca enables reproducible evaluation and advances Spanish text-to-pictogram research.</abstract>
<identifier type="citekey">umeres-cabezudo-2026-pictoeduca</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.1738</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1738/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>34816</start>
<end>34828</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PictoEduca: Building a Dataset for Spanish Text-to-Pictogram Generation
%A Umeres, Alfonso Manuel Paredes
%A Cabezudo, Marco Antonio Sobrevilla
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F umeres-cabezudo-2026-pictoeduca
%X We present PictoEduca, the first large-scale Spanish text-to-pictogram dataset for augmentative and alternative communication (AAC), derived from primary educational materials and grounded in the ARASAAC pictogram repository. The dataset is released with a reproducible pipeline that combines automatic annotation with targeted expert correction, supporting scalable and high-quality corpus construction. We benchmark a rule-based system (ARAWORD) and neural models (T5, LLaMA) under direct text-to-pictogram and two-stage text-to-concept-to-pictogram settings. Results show that the rule-based system remains a strong baseline, while neural models benefit from explicit semantic abstraction, with the two-stage approach improving semantic coherence and reducing ambiguity. We further explore data selection strategies, demonstrating that combining domain similarity with a quality signal yields higher-quality silver data, reduces annotation effort, and improves model performance in low-resource regimes. PictoEduca enables reproducible evaluation and advances Spanish text-to-pictogram research.
%R 10.18653/v1/2026.findings-acl.1738
%U https://aclanthology.org/2026.findings-acl.1738/
%U https://doi.org/10.18653/v1/2026.findings-acl.1738
%P 34816-34828
Markdown (Informal)
[PictoEduca: Building a Dataset for Spanish Text-to-Pictogram Generation](https://aclanthology.org/2026.findings-acl.1738/) (Umeres & Cabezudo, Findings 2026)
ACL