This is a model to detect treatment and disease mentions in texts from health domains. The dataset used for training consists of PubMed's abstracts and tweets with disease mentions, which are publicly available. It has been semi-automatically labeled with a set of regex rules made ad hoc to find treatment-disease links.
The label t is used for treatment (medication, procedures, etc.) and d for disease mentions.
The current F1 score (Seqeval) is 0.91
- Downloads last month
- 42
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.