Downloads · 30 days
64
30% of all-time downloads
KoichiYasuoka/modernbert-base-japanese-wikipedia-ud-square
modernbert-base-japanese-wikipedia-ud-square is a token classification model from KoichiYasuoka. Use it when you need labels on individual words, such as names. The card lists the license as apache-2.0.
This is a ModernBERT model pretrained for POS-tagging and dependency-parsing (using goeswith for subwords), derived from modernbert-base-japanese-wikipedia-upos and UDJapanese-GSDLUW.
Downloads · 30 days
64
30% of all-time downloads
All-time downloads
211
Public
Repo size
1.3 GB
Likes
0
Public
Click a slice to open those files.
.bin644 MB · 99%
From the Hugging Face model README
This is a ModernBERT model pretrained for POS-tagging and dependency-parsing (using goeswith for subwords), derived from modernbert-base-japanese-wikipedia-upos and UD_Japanese-GSDLUW.
from transformers import pipeline
nlp=pipeline("universal-dependencies","KoichiYasuoka/modernbert-base-japanese-wikipedia-ud-square",trust_remote_code=True,aggregation_strategy="simple")
print(nlp("全学年にわたって小学校の国語の教科書に挿し絵が用いられている"))
安岡孝一: 青空文庫ModernBERTモデルによる国語研長単位係り受け解析, 情報処理学会研究報告, Vol.2025-CH-137『人文科学とコンピュータ』, No.10 (2025年2月8日), pp.1-7.