@inproceedings{sugiura-etal-2025-developing,
title = "Developing {J}apanese {CLIP} Models Leveraging an Open-weight {LLM} for Large-scale Dataset Translation",
author = "Sugiura, Issa and
Kurita, Shuhei and
Oda, Yusuke and
Kawahara, Daisuke and
Okazaki, Naoaki",
editor = "Ebrahimi, Abteen and
Haider, Samar and
Liu, Emmy and
Haider, Sammar and
Leonor Pacheco, Maria and
Wein, Shira",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = apr,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-srw.15/",
doi = "10.18653/v1/2025.naacl-srw.15",
pages = "162--170",
ISBN = "979-8-89176-192-6",
abstract = "CLIP is a foundational model that bridges images and text, widely adopted as a key component in numerous vision-language models.However, the lack of large-scale open Japanese image-text pairs poses a significant barrier to the development of Japanese vision-language models.In this study, we constructed a Japanese image-text pair dataset with 1.5 billion examples using machine translation with open-weight LLMs and pre-trained Japanese CLIP models on the dataset.The performance of the pre-trained models was evaluated across seven benchmark datasets, achieving competitive average scores compared to models of similar size without the need for extensive data curation. However, the results also revealed relatively low performance on tasks specific to Japanese culture, highlighting the limitations of translation-based approaches in capturing cultural nuances. Our dataset, models, and code are publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sugiura-etal-2025-developing">
<titleInfo>
<title>Developing Japanese CLIP Models Leveraging an Open-weight LLM for Large-scale Dataset Translation</title>
</titleInfo>
<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">Yusuke</namePart>
<namePart type="family">Oda</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>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</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 (Volume 4: Student Research Workshop)</title>
</titleInfo>
<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">Samar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sammar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Leonor Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shira</namePart>
<namePart type="family">Wein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-192-6</identifier>
</relatedItem>
<abstract>CLIP is a foundational model that bridges images and text, widely adopted as a key component in numerous vision-language models.However, the lack of large-scale open Japanese image-text pairs poses a significant barrier to the development of Japanese vision-language models.In this study, we constructed a Japanese image-text pair dataset with 1.5 billion examples using machine translation with open-weight LLMs and pre-trained Japanese CLIP models on the dataset.The performance of the pre-trained models was evaluated across seven benchmark datasets, achieving competitive average scores compared to models of similar size without the need for extensive data curation. However, the results also revealed relatively low performance on tasks specific to Japanese culture, highlighting the limitations of translation-based approaches in capturing cultural nuances. Our dataset, models, and code are publicly available.</abstract>
<identifier type="citekey">sugiura-etal-2025-developing</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-srw.15</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-srw.15/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>162</start>
<end>170</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing Japanese CLIP Models Leveraging an Open-weight LLM for Large-scale Dataset Translation
%A Sugiura, Issa
%A Kurita, Shuhei
%A Oda, Yusuke
%A Kawahara, Daisuke
%A Okazaki, Naoaki
%Y Ebrahimi, Abteen
%Y Haider, Samar
%Y Liu, Emmy
%Y Haider, Sammar
%Y Leonor Pacheco, Maria
%Y Wein, Shira
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-192-6
%F sugiura-etal-2025-developing
%X CLIP is a foundational model that bridges images and text, widely adopted as a key component in numerous vision-language models.However, the lack of large-scale open Japanese image-text pairs poses a significant barrier to the development of Japanese vision-language models.In this study, we constructed a Japanese image-text pair dataset with 1.5 billion examples using machine translation with open-weight LLMs and pre-trained Japanese CLIP models on the dataset.The performance of the pre-trained models was evaluated across seven benchmark datasets, achieving competitive average scores compared to models of similar size without the need for extensive data curation. However, the results also revealed relatively low performance on tasks specific to Japanese culture, highlighting the limitations of translation-based approaches in capturing cultural nuances. Our dataset, models, and code are publicly available.
%R 10.18653/v1/2025.naacl-srw.15
%U https://aclanthology.org/2025.naacl-srw.15/
%U https://doi.org/10.18653/v1/2025.naacl-srw.15
%P 162-170
Markdown (Informal)
[Developing Japanese CLIP Models Leveraging an Open-weight LLM for Large-scale Dataset Translation](https://aclanthology.org/2025.naacl-srw.15/) (Sugiura et al., NAACL 2025)
ACL