roberta-base-biomedical-clinical-es-ner Open Source Model - For Biomedical Clinical Spanish Text Entity Recognition

Roberta Base Biomedical Clinical Es Ner

Developed by manucos

This model is a fine-tuned version of BSC-LT/roberta-base-biomedical-clinical-es for Named Entity Recognition (NER) tasks on Spanish biomedical clinical texts.

Sequence Labeling

Transformers

Open Source License:Apache-2.0 #Biomedical NER #Clinical Text Analysis #Spanish Language Processing

Downloads 25

Release Time : 6/1/2024

Model Overview

A Named Entity Recognition model specifically designed for Spanish biomedical clinical texts, capable of identifying medical-related entities in the text.

Model Features

Specialized for Biomedical Domain

Optimized specifically for biomedical clinical texts, with excellent performance in this field.

Spanish Language Support

Focused on processing Spanish biomedical texts.

High-precision Recognition

Achieves an F1 score of 0.8801 on the validation set, demonstrating strong performance.

Model Capabilities

Biomedical Named Entity Recognition

Clinical Text Analysis

Spanish Text Processing

Use Cases

Medical Information Processing

Clinical Record Analysis

Extracting medical entities from Spanish clinical records

High-precision recognition with F1 score of 0.8801

Medical Research Literature Processing

Extracting key entity information from biomedical literature

🚀 roberta-base-biomedical-clinical-es-ner

This model is a fine - tuned version of [BSC - LT/roberta - base - biomedical - clinical - es](https://huggingface.co/BSC - LT/roberta - base - biomedical - clinical - es). It offers high - performance NER capabilities in the biomedical and clinical fields, achieving excellent results on the evaluation set.

🚀 Quick Start

This model is a fine - tuned version of [BSC - LT/roberta - base - biomedical - clinical - es](https://huggingface.co/BSC - LT/roberta - base - biomedical - clinical - es) on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3813
Precision: 0.8687
Recall: 0.8919
F1: 0.8801
Accuracy: 0.9374

📚 Documentation

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e - 05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
lr_scheduler_type: linear
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	280	0.3201	0.7961	0.8385	0.8167	0.9130
0.5051	2.0	560	0.2833	0.8245	0.8770	0.8500	0.9282
0.5051	3.0	840	0.2717	0.8459	0.8622	0.8540	0.9262
0.1434	4.0	1120	0.2782	0.8477	0.8904	0.8685	0.9324
0.1434	5.0	1400	0.3119	0.8525	0.8993	0.8753	0.9355
0.0804	6.0	1680	0.3146	0.8639	0.8933	0.8784	0.9366
0.0804	7.0	1960	0.3211	0.8637	0.8919	0.8776	0.9346
0.0475	8.0	2240	0.3523	0.8707	0.8978	0.8840	0.9372
0.0347	9.0	2520	0.3651	0.8434	0.8859	0.8642	0.9335
0.0347	10.0	2800	0.3663	0.8706	0.8874	0.8789	0.9360
0.0241	11.0	3080	0.3756	0.8680	0.8963	0.8819	0.9372
0.0241	12.0	3360	0.3692	0.86	0.8919	0.8756	0.9369
0.0201	13.0	3640	0.3782	0.8631	0.8874	0.8751	0.9360
0.0201	14.0	3920	0.3820	0.8698	0.8904	0.8799	0.9374
0.0172	15.0	4200	0.3813	0.8687	0.8919	0.8801	0.9374

Framework versions

Transformers 4.41.1
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.19.1

📄 License

This model is released under the Apache 2.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご