metadata

language:
  - ja
tags:
  - japanese
  - token-classification
  - pos
  - wikipedia
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。

bert-base-japanese-luw-upos

Model Description

This is a BERT model pre-trained on Japanese Wikipedia texts for POS-tagging, derived from bert-base-japanese-char-extended. Every long-unit-word is tagged by UPOS (Universal Part-Of-Speech).

How to Use

import torch
from transformers import AutoTokenizer,AutoModelForTokenClassification
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/bert-base-japanese-luw-upos")
model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/bert-base-japanese-luw-upos")
s="国境の長いトンネルを抜けると雪国であった。"
p=[model.config.id2label[q] for q in torch.argmax(model(tokenizer.encode(s,return_tensors="pt"))["logits"],dim=2)[0].tolist()[1:-1]]
print(list(zip(s,p)))

KoichiYasuoka
/

bert-base-japanese-luw-upos

bert-base-japanese-luw-upos

Model Description

How to Use

See Also