---
language: ja
license: cc-by-nc-sa-4.0
tags:
- roberta
- medical
mask_token: "[MASK]"
widget:
- text: "この患者は[MASK]と診断された。"
---

# alabnii/jmedroberta-base-sentencepiece

## Model description

This is a Japanese RoBERTa base model pre-trained on academic articles in medical sciences collected by Japan Science and Technology Agency (JST).

This model is released under the [Creative Commons 4.0 International License](https://creativecommons.org/licenses/by-nc-sa/4.0/deed) (CC BY-NC-SA 4.0).

## Datasets used for pre-training

- abstracts (train: 1.6GB (10M sentences), validation: 0.2GB (1.3M sentences))
- abstracts & body texts (train: 0.2GB (1.4M sentences))

## How to use

**Input text must be converted to full-width characters（全角）in advance.**

You can use this model for masked language modeling as follows:
```python
from transformers import AutoModelForMaskedLM, AutoTokenizer

model = AutoModelForMaskedLM.from_pretrained("alabnii/jmedroberta-base-sentencepiece")
model.eval()
tokenizer = AutoTokenizer.from_pretrained("alabnii/jmedroberta-base-sentencepiece")

texts = ['この患者は[MASK]と診断された。']
inputs = tokenizer.batch_encode_plus(texts, return_tensors='pt')
outputs = model(**inputs)
tokenizer.convert_ids_to_tokens(outputs.logits[0][1:-1].argmax(axis=-1))
# ['▁この', '患者は', 'ＡＭＬ', '▁', 'と診断された', '。']
```

Alternatively, you can employ [Fill-mask pipeline](https://huggingface.co/tasks/fill-mask).

```python
from transformers import pipeline
fill = pipeline("fill-mask", model="alabnii/jmedroberta-base-sentencepiece", top_k=10)
fill("この患者は[MASK]と診断された。")
#[{'score': 0.04239409416913986,
#  'token': 7698,
#  'token_str': 'ＡＭＬ',
#  'sequence': 'この患者はＡＭＬ と診断された。'},
# {'score': 0.03562006726861,
#  'token': 3298,
#  'token_str': 'ＳＬＥ',
#  'sequence': 'この患者はＳＬＥ と診断された。'},
# {'score': 0.025064188987016678,
#  'token': 10303,
#  'token_str': 'ＭＤＳ',
#  'sequence': 'この患者はＭＤＳ と診断された。'},
# ...
```

You can fine-tune this model on downstream tasks.

**See also sample Colab notebooks:** https://colab.research.google.com/drive/1BUD3DKOUMqcwIO3X5bYUOsR_wDzgOJcd?usp=sharing

## Tokenization

Each sentence is tokenized into tokens by [SentencePiece (Unigram)](https://huggingface.co/course/chapter6/7).

## Vocabulary

The vocabulary consists of 30000 tokens induced by [SentencePiece (Unigram)](https://huggingface.co/course/chapter6/7).

## Training procedure

The following hyperparameters were used during pre-training:

- learning_rate: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 256
- total_eval_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20000
- training_steps: 2000000
- mixed_precision_training: Native AMP

## Note: Why do we call our model RoBERTa, not BERT?

As the config file suggests, our model is based on HuggingFace's `BertForMaskedLM` class. However, we consider our model as **RoBERTa** for the following reasons:

- We kept training only with max sequence length (= 512) tokens.
- We removed the next sentence prediction (NSP) training objective.
- We introduced dynamic masking (changing the masking pattern in each training iteration).

## Acknowledgements

This work was supported by Japan Japan Science and Technology Agency (JST) AIP Trilateral AI Research (Grant Number: JPMJCR20G9), and Joint Usage/Research Center for Interdisciplinary Large-scale Information Infrastructures (JHPCN) (Project ID: jh221004), in Japan.  
In this research work, we used the "[mdx: a platform for the data-driven future](https://mdx.jp/)".