@inproceedings{tewari-etal-2026-musia,
title = "{MUSIA}: Multilingual Story Illustration Corpus for Cross-Cultural Alignment and Generation",
author = "Tewari, Krishna and
Chanda, Supriya and
Patil, Nirmit and
Pal, Sukomal",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.150/",
doi = "10.63317/3pk9sab3nfuo",
pages = "1914--1924",
abstract = "Recent advances in text-to-image generation have enabled automated visual storytelling, yet most existing datasets remain monolingual and culturally narrow. We introduce MUSIA, a Multilingual Story Illustration Corpus designed to advance research in cross-lingual and culturally grounded narrative illustration. MUSIA comprises bilingual (English-Hindi) story-image pairs drawn from open literary and folk sources, curated to reflect diverse cultural themes, artistic styles, and linguistic structures. Each story includes multiple illustrations aligned at the scene level, accompanied by quality-verified mappings for narrative-visual coherence. To establish a reproducible benchmark, we propose a two-stage baseline combining transformer-based semantic summarization with diffusion-based image generation, achieving strong performance in relevance, visual quality, and consistency. MUSIA represents the first step toward a scalable, culturally inclusive benchmark for multilingual visual storytelling, enabling fair and reproducible research across low-resource and underrepresented languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tewari-etal-2026-musia">
<titleInfo>
<title>MUSIA: Multilingual Story Illustration Corpus for Cross-Cultural Alignment and Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Krishna</namePart>
<namePart type="family">Tewari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Supriya</namePart>
<namePart type="family">Chanda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nirmit</namePart>
<namePart type="family">Patil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sukomal</namePart>
<namePart type="family">Pal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent advances in text-to-image generation have enabled automated visual storytelling, yet most existing datasets remain monolingual and culturally narrow. We introduce MUSIA, a Multilingual Story Illustration Corpus designed to advance research in cross-lingual and culturally grounded narrative illustration. MUSIA comprises bilingual (English-Hindi) story-image pairs drawn from open literary and folk sources, curated to reflect diverse cultural themes, artistic styles, and linguistic structures. Each story includes multiple illustrations aligned at the scene level, accompanied by quality-verified mappings for narrative-visual coherence. To establish a reproducible benchmark, we propose a two-stage baseline combining transformer-based semantic summarization with diffusion-based image generation, achieving strong performance in relevance, visual quality, and consistency. MUSIA represents the first step toward a scalable, culturally inclusive benchmark for multilingual visual storytelling, enabling fair and reproducible research across low-resource and underrepresented languages.</abstract>
<identifier type="citekey">tewari-etal-2026-musia</identifier>
<identifier type="doi">10.63317/3pk9sab3nfuo</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.150/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1914</start>
<end>1924</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MUSIA: Multilingual Story Illustration Corpus for Cross-Cultural Alignment and Generation
%A Tewari, Krishna
%A Chanda, Supriya
%A Patil, Nirmit
%A Pal, Sukomal
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F tewari-etal-2026-musia
%X Recent advances in text-to-image generation have enabled automated visual storytelling, yet most existing datasets remain monolingual and culturally narrow. We introduce MUSIA, a Multilingual Story Illustration Corpus designed to advance research in cross-lingual and culturally grounded narrative illustration. MUSIA comprises bilingual (English-Hindi) story-image pairs drawn from open literary and folk sources, curated to reflect diverse cultural themes, artistic styles, and linguistic structures. Each story includes multiple illustrations aligned at the scene level, accompanied by quality-verified mappings for narrative-visual coherence. To establish a reproducible benchmark, we propose a two-stage baseline combining transformer-based semantic summarization with diffusion-based image generation, achieving strong performance in relevance, visual quality, and consistency. MUSIA represents the first step toward a scalable, culturally inclusive benchmark for multilingual visual storytelling, enabling fair and reproducible research across low-resource and underrepresented languages.
%R 10.63317/3pk9sab3nfuo
%U https://aclanthology.org/2026.lrec-1.150/
%U https://doi.org/10.63317/3pk9sab3nfuo
%P 1914-1924
Markdown (Informal)
[MUSIA: Multilingual Story Illustration Corpus for Cross-Cultural Alignment and Generation](https://aclanthology.org/2026.lrec-1.150/) (Tewari et al., LREC 2026)
ACL