XLM-Roberta base model for biomedical NER

The model has been first trained for medical domain adaptation on English, Spanish, and Italian documents. Afterward, it was fine-tuned on MultiCadrioNER drug extraction task. The model shows the best results in Italian and scores in top-5 for English and Spanish.

Here you can find the paper with more details: https://ceur-ws.org/Vol-3740/paper-04.pdf

Downloads last month: 6

Inference Examples

Token Classification

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.