README.md

metadata

language:
  - ja
tags:
  - japanese
  - token-classification
  - pos
datasets:
  - universal_dependencies
license: cc-by-sa-4.0
pipeline_tag: token-classification
widget:
  - text: 国境の長いトンネルを抜けると雪国であった。

gpt2-small-japanese-upos

Model Description

This is a GPT-2 model for POS-tagging and dependency-parsing, derived from gpt2-small-japanese-char. Every short-unit-word is tagged by UPOS (Universal Part-Of-Speech) and FEATS.

How to Use

from transformers import pipeline
nlp=pipeline("upos","KoichiYasuoka/gpt2-small-japanese-upos",trust_remote_code=True,aggregation_strategy="simple")
print(nlp("国境の長いトンネルを抜けると雪国であった。"))

or

import esupar
nlp=esupar.load("KoichiYasuoka/gpt2-small-japanese-upos")
print(nlp("国境の長いトンネルを抜けると雪国であった。"))

See Also

esupar: Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa/DeBERTa models