Commit
·
fce645c
1
Parent(s):
66f60be
Add README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: es
|
| 3 |
+
tags:
|
| 4 |
+
- biomedical
|
| 5 |
+
- clinical
|
| 6 |
+
- spanish
|
| 7 |
+
- XLM_R_Galen
|
| 8 |
+
license: mit
|
| 9 |
+
datasets:
|
| 10 |
+
- "PlanTL-GOB-ES/pharmaconer"
|
| 11 |
+
metrics:
|
| 12 |
+
- f1
|
| 13 |
+
|
| 14 |
+
model-index:
|
| 15 |
+
- name: IIC/XLM_R_Galen-pharmaconer
|
| 16 |
+
results:
|
| 17 |
+
- task:
|
| 18 |
+
type: token-classification
|
| 19 |
+
dataset:
|
| 20 |
+
name: pharmaconer
|
| 21 |
+
type: PlanTL-GOB-ES/pharmaconer
|
| 22 |
+
split: test
|
| 23 |
+
metrics:
|
| 24 |
+
- name: f1
|
| 25 |
+
type: f1
|
| 26 |
+
value: 0.915
|
| 27 |
+
pipeline_tag: token-classification
|
| 28 |
+
widget:
|
| 29 |
+
- text: "Se realizó estudio analítico destacando incremento de niveles de PTH y vitamina D (103,7 pg/ml y 272 ng/ml, respectivamente), atribuidos al exceso de suplementación de vitamina D."
|
| 30 |
+
- text: " Por el hallazgo de múltiples fracturas por estrés, se procedió a estudio en nuestras consultas, realizándose análisis con función renal, calcio sérico y urinario, calcio iónico, magnesio y PTH, que fueron normales."
|
| 31 |
+
- text: "Se solicitó una analítica que incluía hemograma, bioquímica, anticuerpos antinucleares (ANA) y serologías, examen de orina, así como biopsia de la lesión. Los resultados fueron normales, con ANA, anti-Sm, anti-RNP, anti-SSA, anti-SSB, anti-Jo1 y anti-Scl70 negativos."
|
| 32 |
+
|
| 33 |
+
---
|
| 34 |
+
|
| 35 |
+
# XLM_R_Galen-pharmaconer
|
| 36 |
+
|
| 37 |
+
This model is a finetuned version of XLM_R_Galen for the pharmaconer dataset used in a benchmark in the paper TODO. The model has a F1 of 0.915
|
| 38 |
+
|
| 39 |
+
Please refer to the original publication for more information TODO LINK
|
| 40 |
+
|
| 41 |
+
## Parameters used
|
| 42 |
+
|
| 43 |
+
| parameter | Value |
|
| 44 |
+
|-------------------------|:-----:|
|
| 45 |
+
| batch size | 16 |
|
| 46 |
+
| learning rate | 3e-05 |
|
| 47 |
+
| classifier dropout | 0.1 |
|
| 48 |
+
| warmup ratio | 0 |
|
| 49 |
+
| warmup steps | 0 |
|
| 50 |
+
| weight decay | 0 |
|
| 51 |
+
| optimizer | AdamW |
|
| 52 |
+
| epochs | 10 |
|
| 53 |
+
| early stopping patience | 3 |
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
## BibTeX entry and citation info
|
| 57 |
+
|
| 58 |
+
```bibtex
|
| 59 |
+
TODO
|
| 60 |
+
```
|
| 61 |
+
|