This is a model for complex word identification (CWI) of Spanish medical texts, based on the multilingual DeBERTa vs 3 (mDeBERTa).
The model was fine-tuned on a corpus of 225 texts for patients (162575 tokens) to identify complex words (CW).
Results (test set)
| Class | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|
| CW | 79.05 (±1.39) | 79.01 (±0.70) | 79.02 (±0.65) | 94.86 (±0.22) |
*Results are the average of 3 experimental rounds.
If you use this model or want to have more details about the experiments and the training details, take a look at our article:
@article{2025CWI,
title={Complex Word Identification for Lexical Simplification in Spanish Texts for Patients},
author={Ortega-Riba, Federico and Campillos-Llanos, Leonardo and Samy, Doaa},
journal={Procesamiento del lenguaje natural},
volume={74},
year={2025}
}
- Downloads last month
- 49
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.