| --- |
| language: es |
| tags: |
| - biomedical |
| - clinical |
| - spanish |
| - mdeberta-v3-base |
| license: mit |
| datasets: |
| - "chizhikchi/CARES" |
| metrics: |
| - f1 |
|
|
| model-index: |
| - name: IIC/mdeberta-v3-base-caresA |
| results: |
| - task: |
| type: multi-label-classification |
| dataset: |
| name: Cares Area |
| type: chizhikchi/CARES |
| split: test |
| metrics: |
| - name: f1 |
| type: f1 |
| value: 0.993 |
| pipeline_tag: text-classification |
|
|
| --- |
| |
| # mdeberta-v3-base-caresA |
|
|
| This model is a finetuned version of mdeberta-v3-base for the cantemist dataset used in a benchmark in the paper `A comparative analysis of Spanish Clinical encoder-based models on NER and classification tasks`. The model has a F1 of 0.993 |
|
|
| Please refer to the [original publication](https://doi.org/10.1093/jamia/ocae054) for more information. |
|
|
| ## Parameters used |
|
|
| | parameter | Value | |
| |-------------------------|:-----:| |
| | batch size | 16 | |
| | learning rate | 4e-05 | |
| | classifier dropout | 0.2 | |
| | warmup ratio | 0 | |
| | warmup steps | 0 | |
| | weight decay | 0 | |
| | optimizer | AdamW | |
| | epochs | 10 | |
| | early stopping patience | 3 | |
|
|
|
|
| ## BibTeX entry and citation info |
|
|
| ```bibtext |
| @article{10.1093/jamia/ocae054, |
| author = {García Subies, Guillem and Barbero Jiménez, Álvaro and Martínez Fernández, Paloma}, |
| title = {A comparative analysis of Spanish Clinical encoder-based models on NER and classification tasks}, |
| journal = {Journal of the American Medical Informatics Association}, |
| volume = {31}, |
| number = {9}, |
| pages = {2137-2146}, |
| year = {2024}, |
| month = {03}, |
| issn = {1527-974X}, |
| doi = {10.1093/jamia/ocae054}, |
| url = {https://doi.org/10.1093/jamia/ocae054}, |
| } |
| ``` |
|
|
|
|
