German Medical BERT
This is a fine-tuned model on the Medical domain for the German language and based on German BERT. This model has only been trained to improve on-target tasks (Masked Language Model). It can later be used to perform a downstream task of your needs, while I performed it for the NTS-ICD-10 text classification task.
Overview
Language model: bert-base-german-cased
Language: German
Fine-tuning: Medical articles (diseases, symptoms, therapies, etc..)
Eval data: NTS-ICD-10 dataset (Classification)
Infrastructure: Google Colab
Details
- We fine-tuned using Pytorch with Huggingface library on Colab GPU.
- With standard parameter settings for fine-tuning as mentioned in the original BERT paper.
- Although had to train for up to 25 epochs for classification.
Performance (Micro precision, recall, and f1 score for multilabel code classification)
| Models | P | R | F1 |
|---|---|---|---|
| German BERT | 86.04 | 75.82 | 80.60 |
| German MedBERT-256 (fine-tuned) | 87.41 | 77.97 | 82.42 |
| German MedBERT-512 (fine-tuned) | 87.75 | 78.26 | 82.73 |
Author
Manjil Shrestha: shresthamanjil21 [at] gmail.com
Related Paper: Report
Get in touch: LinkedIn
- Downloads last month
- 2,131
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.