Hi, community. I am trying to build an app that extracts Patient Sensitive Data, Diagnoses, Procedures, and Treatments from a Patient Note. The Patient notes are in Norwegian. My goal is to reach 90%+ accuracy. What do you recommend on how to achieve this?
Should I fine-tune it into English first and then translate it into Norwegian? Or should I fine-tune directly based on Norwegian data?
Please consider that I can access a high volume of already anonymized quality patient data in English and a minimal volume not anonymized in Norwegian.
Looking forward to your feedback 