@inproceedings{sasagawa-etal-2025-constructing,
title = "Constructing Multimodal Datasets from Scratch for Rapid Development of a {J}apanese Visual Language Model",
author = "Sasagawa, Keito and
Maeda, Koki and
Sugiura, Issa and
Kurita, Shuhei and
Okazaki, Naoaki and
Kawahara, Daisuke",
editor = "Dziri, Nouha and
Ren, Sean (Xiang) and
Diao, Shizhe",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-demo.38/",
doi = "10.18653/v1/2025.naacl-demo.38",
pages = "470--484",
ISBN = "979-8-89176-191-9",
abstract = "To develop high-performing Visual Language Models (VLMs), it is essential to prepare multimodal resources, such as image-text pairs, interleaved data, and instruction data. While multimodal resources for English are abundant, there is a significant lack of corresponding resources for non-English languages, such as Japanese. To address this problem, we take Japanese as a non-English language and propose Japanese multimodal datasets for rapidly developing a Japanese multimodal model. We collect Japanese image-text pairs and interleaved data from web archives and generate Japanese instruction data using an existing large language model and a VLM. Our experimental results show that a VLM trained on these native datasets outperforms those relying on machine-translated content. The resulting VLM, dataset and code used for training is publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sasagawa-etal-2025-constructing">
<titleInfo>
<title>Constructing Multimodal Datasets from Scratch for Rapid Development of a Japanese Visual Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keito</namePart>
<namePart type="family">Sasagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koki</namePart>
<namePart type="family">Maeda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Issa</namePart>
<namePart type="family">Sugiura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuhei</namePart>
<namePart type="family">Kurita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daisuke</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nouha</namePart>
<namePart type="family">Dziri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="given">(Xiang)</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shizhe</namePart>
<namePart type="family">Diao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-191-9</identifier>
</relatedItem>
<abstract>To develop high-performing Visual Language Models (VLMs), it is essential to prepare multimodal resources, such as image-text pairs, interleaved data, and instruction data. While multimodal resources for English are abundant, there is a significant lack of corresponding resources for non-English languages, such as Japanese. To address this problem, we take Japanese as a non-English language and propose Japanese multimodal datasets for rapidly developing a Japanese multimodal model. We collect Japanese image-text pairs and interleaved data from web archives and generate Japanese instruction data using an existing large language model and a VLM. Our experimental results show that a VLM trained on these native datasets outperforms those relying on machine-translated content. The resulting VLM, dataset and code used for training is publicly available.</abstract>
<identifier type="citekey">sasagawa-etal-2025-constructing</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-demo.38</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-demo.38/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>470</start>
<end>484</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Constructing Multimodal Datasets from Scratch for Rapid Development of a Japanese Visual Language Model
%A Sasagawa, Keito
%A Maeda, Koki
%A Sugiura, Issa
%A Kurita, Shuhei
%A Okazaki, Naoaki
%A Kawahara, Daisuke
%Y Dziri, Nouha
%Y Ren, Sean (Xiang)
%Y Diao, Shizhe
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (System Demonstrations)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-191-9
%F sasagawa-etal-2025-constructing
%X To develop high-performing Visual Language Models (VLMs), it is essential to prepare multimodal resources, such as image-text pairs, interleaved data, and instruction data. While multimodal resources for English are abundant, there is a significant lack of corresponding resources for non-English languages, such as Japanese. To address this problem, we take Japanese as a non-English language and propose Japanese multimodal datasets for rapidly developing a Japanese multimodal model. We collect Japanese image-text pairs and interleaved data from web archives and generate Japanese instruction data using an existing large language model and a VLM. Our experimental results show that a VLM trained on these native datasets outperforms those relying on machine-translated content. The resulting VLM, dataset and code used for training is publicly available.
%R 10.18653/v1/2025.naacl-demo.38
%U https://aclanthology.org/2025.naacl-demo.38/
%U https://doi.org/10.18653/v1/2025.naacl-demo.38
%P 470-484
Markdown (Informal)
[Constructing Multimodal Datasets from Scratch for Rapid Development of a Japanese Visual Language Model](https://aclanthology.org/2025.naacl-demo.38/) (Sasagawa et al., NAACL 2025)
ACL