Release of Pre-Trained Models for the Japanese Language

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sawada, Kei, Zhao, Tianyu, Shing, Makoto, Mitsui, Kentaro, Kaga, Akio, Hono, Yukiya, Wakatsuki, Toshiaki, Mitsuda, Koh
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917628881141760
author Sawada, Kei
Zhao, Tianyu
Shing, Makoto
Mitsui, Kentaro
Kaga, Akio
Hono, Yukiya
Wakatsuki, Toshiaki
Mitsuda, Koh
author_facet Sawada, Kei
Zhao, Tianyu
Shing, Makoto
Mitsui, Kentaro
Kaga, Akio
Hono, Yukiya
Wakatsuki, Toshiaki
Mitsuda, Koh
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2404_01657
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Release of Pre-Trained Models for the Japanese Language
Sawada, Kei
Zhao, Tianyu
Shing, Makoto
Mitsui, Kentaro
Kaga, Akio
Hono, Yukiya
Wakatsuki, Toshiaki
Mitsuda, Koh
Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Audio and Speech Processing
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.
title Release of Pre-Trained Models for the Japanese Language
topic Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2404.01657