roberta-base-bne-capitel-ner Open Source Model - Supports Precise Named Entity Recognition for Spanish

Roberta Base Bne Capitel Ner

Developed by BSC-LT

This model is a Spanish named entity recognition model based on the RoBERTa architecture, pretrained on the large-scale corpus from the Spanish National Library and fine-tuned on the CAPITEL NER dataset.

Sequence Labeling

Transformers

Supports Multiple LanguagesOpen Source License:Apache-2.0 #Spanish NER #High F1 Score #BNE Pretraining

Downloads 37

Release Time : 3/2/2022

Model Overview

This model is specifically designed for named entity recognition tasks in Spanish texts, capable of identifying entities such as person names, place names, and organization names in text.

Model Features

Large-scale Pretraining

Pretrained on 570GB of cleaned corpus from the Spanish National Library

Domain-specific Fine-tuning

Specially optimized on the Named Entity Recognition task dataset from the CAPITEL benchmark

High Performance

Achieves an F1 score of 0.896 on NER tasks

Model Capabilities

Spanish text processing

Named Entity Recognition

Natural Language Understanding

Use Cases

Information Extraction

News Text Entity Recognition

Extract person names, place names, and organization names from Spanish news

High-accuracy entity recognition

Document Automation Processing

Automatically process entity information in Spanish documents

Improved document processing efficiency

🚀 Spanish RoBERTa-base for CAPITEL NER

This is a Spanish RoBERTa-base model trained on BNE and finetuned for the CAPITEL Named Entity Recognition (NER) dataset, aiming to provide high - quality NER services for Spanish text.

🚀 Quick Start

This model is a masked language model for Spanish based on the Transformer architecture. It builds upon the RoBERTa base model. The pre - training process used the largest Spanish corpus to date, with a total of 570GB of clean and deduplicated text. This corpus was compiled from web crawlings by the National Library of Spain (Biblioteca Nacional de España) from 2009 to 2019.

The original pre - trained model can be found here: https://huggingface.co/BSC-TeMU/roberta-base-bne

⚠️ Important Note

THIS MODEL HAS BEEN MOVED TO THE FOLLOWING URL AND WILL SOON BE REMOVED: https://huggingface.co/PlanTL-GOB-ES/roberta-base-bne-capitel-ner

✨ Features

Language: Spanish
License: Apache - 2.0
Tags: "national library of spain", "spanish", "bne", "capitel", "ner"
Datasets: "bne", "capitel"
Metrics: "f1"

Property	Details
Model Type	Transformer - based masked language model for Spanish
Training Data	Compiled from web crawlings by the National Library of Spain from 2009 to 2019, with 570GB of clean and deduplicated text

📚 Documentation

Dataset

The dataset used is from the CAPITEL competition at IberLEF 2020 (sub - task 1).

Evaluation and results

F1 Score: 0.8960

For evaluation details visit our GitHub repository.

Citing

Check out our paper for all the details: https://arxiv.org/abs/2107.07253

@misc{gutierrezfandino2021spanish,
      title={Spanish Language Models}, 
      author={Asier Gutiérrez-Fandiño and Jordi Armengol-Estapé and Marc Pàmies and Joan Llop-Palao and Joaquín Silveira-Ocampo and Casimiro Pio Carrino and Aitor Gonzalez-Agirre and Carme Armentano-Oller and Carlos Rodriguez-Penagos and Marta Villegas},
      year={2021},
      eprint={2107.07253},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

📄 License

This project is licensed 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