KoichiYasuoka's picture
dependency-parsing
80c10e9
|
raw
history blame
1.35 kB
metadata
language:
  - ja
tags:
  - japanese
  - token-classification
  - pos
base_model: KoichiYasuoka/modernbert-base-japanese-aozora
datasets:
  - universal_dependencies
license: apache-2.0
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。

modernbert-base-japanese-aozora-upos

Model Description

This is a ModernBERT model pre-trained on 青空文庫 texts for POS-tagging and dependency-parsing, derived from modernbert-base-japanese-aozora. 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/modernbert-base-japanese-aozora-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/modernbert-base-japanese-aozora-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/GPT models