Downloads · 30 days
6
15% of all-time downloads
aaaksenova/xlmr_medical
xlmr_medical is a token classification model from aaaksenova. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.
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 Itali…
Downloads · 30 days
6
15% of all-time downloads
All-time downloads
39
Public
Repo size
3.4 GB
Likes
0
Public
Click a slice to open those files.
.bin1.1 GB · 98%
From the Hugging Face model README
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