R

Roberta Base Bne Capitel Ner

Developed by PlanTL-GOB-ES
Spanish named entity recognition model based on RoBERTa architecture, pre-trained on BNE corpus and fine-tuned on CAPITEL-NERC dataset
Downloads 8,221
Release Time : 3/2/2022

Model Overview

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

Model Features

Large-scale pre-training
Pre-trained on 570GB of cleaned Spanish text
Domain-specific fine-tuning
Fine-tuned specifically for named entity recognition tasks on the CAPITEL-NERC competition dataset
High performance
Achieved an F1 score of 89.60 on the CAPITEL-NERC test set, outperforming similar baseline models

Model Capabilities

Spanish text processing
Named entity recognition
Person name recognition
Place name recognition
Organization name recognition

Use Cases

Information extraction
Document entity extraction
Automatically extract entity information such as person names and place names from Spanish documents
Accurately identifies named entities in text
Content classification
Classify document content based on identified entities
Improves document classification accuracy
Knowledge graph construction
Entity relation extraction
Serve as a preliminary processing step for knowledge graph construction
Provides foundation for subsequent relation extraction
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase