metadata
license: apache-2.0
base_model: microsoft/mdeberta-v3-base
datasets:
- HiTZ/casimedicos-squad
language:
- en
- es
- fr
- it
metrics:
- f1
pipeline_tag: question-answering
library_name: transformers
widget:
- text: >-
In osteoporosis, one of the main risks associated with the increased risk
of fracture is low adherence to treatment, so answer 1 is correct. Answer
2 is found in the SER guidelines, which confirm that some studies conclude
that bone remodeling markers can be useful for early monitoring of
adherence and response to treatment. Answer 4 is correct because again in
the SER 2019 guidelines they quote: "The current scientific evidence
allows us to affirm that neither increasing dietary calcium nor taking
calcium supplements alone protects against the appearance of fractures".
Therefore, the correct answer to this question is option 3. Patients on
pharmacological treatment for OP should use calcium and vitamin D
supplements because practically all clinical trials that have demonstrated
efficacy of antiosteoporotic drugs routinely include calcium supplements
and cholecalciferol (vitamin D3), but not in monotherapy.
- text: >-
La disuria se resolvió más rápidamente en los pacientes implantados con
103Pd, pero no se vio afectada por el uso de radioterapia suplementaria
y/o terapia de privación de andrógenos.
- text: >-
La dysurie s'est résorbée plus rapidement chez les patients implantés avec
du 103Pd, mais n'a pas été affectée par l'utilisation d'une radiothérapie
complémentaire et/ou d'une thérapie de privation d'androgènes.
- text: >-
La disuria si è risolta più rapidamente nei pazienti impiantati con 103Pd,
ma non è stata influenzata dall'uso della radioterapia supplementare e/o
della terapia di deprivazione androgenica.
mDeBERTa-base for Multilingual Correct Explanation Extraction in the Medical Domain
This model is a fine-tuned version of mdeberta-v3-base for a novel extractive task which consists of identifying the explanation of the correct answer written by medical doctors. The model has been fine-tuned using the multilingual https://huggingface.co/datasets/HiTZ/casimedicos-squad dataset.
Performance
F1 partial match scores (as defined in SQuAD extractive QA task are reported in the following table:
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.2
Contact: Anar Yeginbergen and Rodrigo Agerri HiTZ Center - Ixa, University of the Basque Country UPV/EHU