|
--- |
|
language: |
|
- "ja" |
|
tags: |
|
- "japanese" |
|
- "token-classification" |
|
- "pos" |
|
base_model: ku-nlp/gpt2-medium-japanese-char |
|
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-medium-japanese-upos |
|
|
|
## Model Description |
|
|
|
This is a GPT-2 model for POS-tagging and dependency-parsing, derived from [gpt2-medium-japanese-char](https://huggingface.co/ku-nlp/gpt2-medium-japanese-char). Every short-unit-word is tagged by [UPOS](https://universaldependencies.org/u/pos/) (Universal Part-Of-Speech) and [FEATS](https://universaldependencies.org/u/feat/). |
|
|
|
## How to Use |
|
|
|
```py |
|
from transformers import pipeline |
|
nlp=pipeline("upos","KoichiYasuoka/gpt2-medium-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 |
|
|
|
```py |
|
import esupar |
|
nlp=esupar.load("KoichiYasuoka/gpt2-medium-japanese-upos") |
|
print(nlp("国境の長いトンネルを抜けると雪国であった。")) |
|
``` |
|
|
|
## Reference |
|
|
|
安岡孝一: [GPT系モデルの系列ラベリングによる品詞付与](http://hdl.handle.net/2433/288964), 東洋学へのコンピュータ利用, 第38回研究セミナー (2024年7月26日), pp.3-10. |
|
|
|
## See Also |
|
|
|
[esupar](https://github.com/KoichiYasuoka/esupar): Tokenizer POS-tagger and Dependency-parser with BERT/RoBERTa/DeBERTa models |
|
|
|
|
