roberta-large-japanese-aozora-char

Model Description

This is a RoBERTa model pre-trained on 青空文庫 texts with character tokenizer. You can fine-tune roberta-large-japanese-aozora-char for downstream tasks, such as POS-tagging, dependency-parsing, and so on.

How to Use

from transformers import AutoTokenizer,AutoModelForMaskedLM
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/roberta-large-japanese-aozora-char")
model=AutoModelForMaskedLM.from_pretrained("KoichiYasuoka/roberta-large-japanese-aozora-char")

Reference

安岡孝一: Transformersと国語研長単位による日本語係り受け解析モデルの製作, 情報処理学会研究報告, Vol.2022-CH-128, No.7 (2022年2月), pp.1-8.