README.md

metadata

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

deberta-large-japanese-wikipedia-luw-upos

Model Description

This is a DeBERTa(V2) model pre-trained on Japanese Wikipedia and 青空文庫 texts for POS-tagging and dependency-parsing, derived from deberta-large-japanese-wikipedia. Every long-unit-word is tagged by UPOS (Universal Part-Of-Speech) and FEATS.

How to Use

import torch
from transformers import AutoTokenizer,AutoModelForTokenClassification
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/deberta-large-japanese-wikipedia-luw-upos")
model=AutoModelForTokenClassification.from_pretrained("KoichiYasuoka/deberta-large-japanese-wikipedia-luw-upos")
s="国境の長いトンネルを抜けると雪国であった。"
t=tokenizer.tokenize(s)
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(t,p)))

or

import esupar
nlp=esupar.load("KoichiYasuoka/deberta-large-japanese-wikipedia-luw-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