gpt2-medium-japanese-unidic-ud-causal
Model Description
This is a GPT-2 model pretrained for POS-tagging and dependency-parsing, derived from gpt2-medium-japanese-unidic-upos and UD_Japanese-GSDLUW.
How to Use
from transformers import pipeline
nlp=pipeline("universal-dependencies","KoichiYasuoka/gpt2-medium-japanese-unidic-ud-causal",trust_remote_code=True)
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"))
fugashi and unidic-lite are required.
Reference
安岡孝一: GPT系言語モデルによる国語研長単位係り受け解析, 人文科学とコンピュータシンポジウム「じんもんこん2024」論文集 (2024年12月), pp.83-90.
- Downloads last month
- 3
Model tree for KoichiYasuoka/gpt2-medium-japanese-unidic-ud-causal
Base model
okazaki-lab/japanese-gpt2-medium-unidic