You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Just to check. Would it be possible to use BioBert directly to obtain the 4 entities type - gene, drug, disease, species? The labels i obtained now are B-MISC etc..
The text was updated successfully, but these errors were encountered:
Depends on what you mean with „directly“. You definitely need to fine-tune, as BioBert pre-trained is basically just a language model. If you do finetune, then yes, that’s possibly. But you need a dataset annotated with these 4 tags and need to change the tags list and tag_map in pred_ner.py accordingly.
Just to check. Would it be possible to use BioBert directly to obtain the 4 entities type - gene, drug, disease, species? The labels i obtained now are B-MISC etc..
The text was updated successfully, but these errors were encountered: