gmichalo

For the fasttext model, I tested the model on Reuters and the AAPD dataset and the new version get the exact same results as the previous version as it was...

Hello, We do not provide the weights for each individual task but we have shared a notebook that can be used to train UmlsBERT on the MedNLI task: https://github.com/gmichalo/UmlsBERT/blob/master/experiments/MedNLI_task.ipynb

Thank you for your interest in the UmlsBERT. The license that we have included in the repo is MIT License

Thank you for your interest in UmlsBert. Yes, you are correct. In this version of UmlsBERT we identified medical words in the vocabulary of the BERT model. When you pass...

Thank you for your interest in UmlsBert. You can find a Jupiter notebook for the NER task in : https://github.com/gmichalo/UmlsBERT/blob/master/experiments/NER_task.ipynb where we have an example-code for UmlsBert and the standard...

Thank you for your interest in UmlsBert. For the creation of UmlsBert, we used the pytorch and the huggingface library. However, at the present time, in order to use UmlsBERT...