|
--- |
|
language: ja |
|
tags: |
|
- exbert |
|
license: cc-by-sa-4.0 |
|
datasets: |
|
- wikipedia |
|
- cc100 |
|
mask_token: "[MASK]" |
|
widget: |
|
- text: "早稲田 大学 で 自然 言語 処理 を [MASK] する 。" |
|
--- |
|
|
|
# nlp-waseda/roberta-base-japanese |
|
|
|
## Model description |
|
|
|
This is a Japanese RoBERTa model pretrained on Japanese Wikipedia and the Japanese portion of CC-100. |
|
|
|
## How to use |
|
|
|
```python |
|
from transformers import AutoTokenizer,AutoModelForMaskedLM |
|
tokenizer=AutoTokenizer.from_pretrained("nlp-waseda/roberta-base-japanese") |
|
model=AutoModelForMaskedLM.from_pretrained("nlp-waseda/roberta-base-japanese") |
|
``` |
|
|
|
## Tokenization |
|
|
|
The input text should be segmented into words by [Juman++](https://github.com/ku-nlp/jumanpp) in advance. Each word is tokenized into subwords by [sentencepiece](https://github.com/google/sentencepiece). |
|
|
|
## Vocabulary |
|
|
|
## Training procedure |
|
|