bert-base-japanese-v3 is a BERT-base model pretrained on Japanese text from CC-100 and jawiki using whole word masking with the unidic-lite tokenizer. It serves as a strong foundation for Japanese natural language processing tasks such as classification, named entity recognition, and question answering. The model is distributed via the Hugging Face Transformers library.
Bert Base Japanese is an Other AI product. It focuses on providing high-quality Japanese language understanding for downstream NLP tasks. Bert Base Japanese is an open-source project aimed at NLP researchers and developers. The project is open source (Apache-2.0). The product ships for the web and API.
It is developed by Tohoku NLP (Japan), and the product first shipped in 2018. The GitHub repository has been archived. Among its 3 catalogued features are Japanese NLP, BERT, and Whole Word Masking.
Latest indexed changes and source events
tohoku-nlp/bert-base-japanese-v3 verified by the PulseGate indexer
⚠ Archived