Our model focuses on Biomedical Named Entity Recognition (NER) in Spanish clinical texts, crucial for automated information extraction in medical research and treatment improvements. It proposes a novel approach using a Multi-Head Conditional Random Field (CRF) classifier to tackle multi-class NER tasks, overcoming challenges of overlapping entity instances. The classes it recognizes include symptoms, procedures, diseases, chemicals, and proteins.
We provide 4 different models, available as branches of this repository.
Authors:
Note we do not take any liability for the use of the model in any professional/medical domain. The model is intended for academic purposes only. It performs Named Entity Recognition over 5 classes namely: SYMPTOM PROCEDURE DISEASE PROTEIN CHEMICAL
Please refer to our GitHub repository for more information on how to train the model and run inference: IEETA Multi-Head-CRF GitHub
The training data can be found on IEETA/SPACCC-Spanish-NER, which is further described on the dataset card. The dataset used consists of 4 seperate datasets:
The models were trained using an Nvidia Quadro RTX 8000. The models for 5 classes took approximately 1 hour to train and occupy around 1GB of disk space. Additionally, this model shows linear complexity (+8 minutes) per entity class to classify.
The testing data can be found on IEETA/SPACCC-Spanish-NER, which is further described on the dataset card.
The models were evaluated using the micro-averaged F1-score metric, the standard for entity recognition tasks.
We provide 4 separate models with various hyperparameter changes:
| HLs per head | Augmentation | Percentage Tags | Augmentation Probability | F1 |
|---|---|---|---|---|
| 3 | Random | 0.25 | 0.50 | 78.73 |
| 3 | Unknown | 0.50 | 0.25 | 78.50 |
| 3 | None | - | - | 78.89 |
| 1 | Random | 0.25 | 0.50 | 78.89 |
All models are trained with a context size of 32 tokens for 60 epochs.
BibTeX:
[Awaiting Publication]
