@inproceedings{sawada-etal-2024-release,
title = "Release of Pre-Trained Models for the {J}apanese Language",
author = "Sawada, Kei and
Zhao, Tianyu and
Shing, Makoto and
Mitsui, Kentaro and
Kaga, Akio and
Hono, Yukiya and
Wakatsuki, Toshiaki and
Mitsuda, Koh",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1213",
pages = "13898--13905",
abstract = "AI democratization aims to create a world in which the average person can utilize AI techniques. To achieve this goal, numerous research institutes have attempted to make their results accessible to the public. In particular, large pre-trained models trained on large-scale data have shown unprecedented potential, and their release has had a significant impact. However, most of the released models specialize in the English language, and thus, AI democratization in non-English-speaking communities is lagging significantly. To reduce this gap in AI access, we released Generative Pre-trained Transformer (GPT), Contrastive Language and Image Pre-training (CLIP), Stable Diffusion, and Hidden-unit Bidirectional Encoder Representations from Transformers (HuBERT) pre-trained in Japanese. By providing these models, users can freely interface with AI that aligns with Japanese cultural values and ensures the identity of Japanese culture, thus enhancing the democratization of AI. Additionally, experiments showed that pre-trained models specialized for Japanese can efficiently achieve high performance in Japanese tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sawada-etal-2024-release">
<titleInfo>
<title>Release of Pre-Trained Models for the Japanese Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kei</namePart>
<namePart type="family">Sawada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyu</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Shing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Mitsui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Akio</namePart>
<namePart type="family">Kaga</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yukiya</namePart>
<namePart type="family">Hono</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Wakatsuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koh</namePart>
<namePart type="family">Mitsuda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>AI democratization aims to create a world in which the average person can utilize AI techniques. To achieve this goal, numerous research institutes have attempted to make their results accessible to the public. In particular, large pre-trained models trained on large-scale data have shown unprecedented potential, and their release has had a significant impact. However, most of the released models specialize in the English language, and thus, AI democratization in non-English-speaking communities is lagging significantly. To reduce this gap in AI access, we released Generative Pre-trained Transformer (GPT), Contrastive Language and Image Pre-training (CLIP), Stable Diffusion, and Hidden-unit Bidirectional Encoder Representations from Transformers (HuBERT) pre-trained in Japanese. By providing these models, users can freely interface with AI that aligns with Japanese cultural values and ensures the identity of Japanese culture, thus enhancing the democratization of AI. Additionally, experiments showed that pre-trained models specialized for Japanese can efficiently achieve high performance in Japanese tasks.</abstract>
<identifier type="citekey">sawada-etal-2024-release</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1213</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>13898</start>
<end>13905</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Release of Pre-Trained Models for the Japanese Language
%A Sawada, Kei
%A Zhao, Tianyu
%A Shing, Makoto
%A Mitsui, Kentaro
%A Kaga, Akio
%A Hono, Yukiya
%A Wakatsuki, Toshiaki
%A Mitsuda, Koh
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F sawada-etal-2024-release
%X AI democratization aims to create a world in which the average person can utilize AI techniques. To achieve this goal, numerous research institutes have attempted to make their results accessible to the public. In particular, large pre-trained models trained on large-scale data have shown unprecedented potential, and their release has had a significant impact. However, most of the released models specialize in the English language, and thus, AI democratization in non-English-speaking communities is lagging significantly. To reduce this gap in AI access, we released Generative Pre-trained Transformer (GPT), Contrastive Language and Image Pre-training (CLIP), Stable Diffusion, and Hidden-unit Bidirectional Encoder Representations from Transformers (HuBERT) pre-trained in Japanese. By providing these models, users can freely interface with AI that aligns with Japanese cultural values and ensures the identity of Japanese culture, thus enhancing the democratization of AI. Additionally, experiments showed that pre-trained models specialized for Japanese can efficiently achieve high performance in Japanese tasks.
%U https://aclanthology.org/2024.lrec-main.1213
%P 13898-13905
Markdown (Informal)
[Release of Pre-Trained Models for the Japanese Language](https://aclanthology.org/2024.lrec-main.1213) (Sawada et al., LREC-COLING 2024)
ACL
- Kei Sawada, Tianyu Zhao, Makoto Shing, Kentaro Mitsui, Akio Kaga, Yukiya Hono, Toshiaki Wakatsuki, and Koh Mitsuda. 2024. Release of Pre-Trained Models for the Japanese Language. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 13898–13905, Torino, Italia. ELRA and ICCL.