Bert Base Multilingual Cased Finetuned Igbo
B
Bert Base Multilingual Cased Finetuned Igbo
Developed by Davlan
This is a BERT model optimized for the Igbo language, obtained by fine-tuning on top of the multilingual BERT, and it performs better than the base multilingual model in Igbo text processing tasks.
Downloads 16
Release Time : 3/2/2022
Model Overview
This model is a BERT model fine-tuned on Igbo text based on bert-base-multilingual-cased, specifically designed for natural language processing tasks in Igbo.
Model Features
Igbo optimization
Specially fine-tuned for Igbo, with better performance compared to the base multilingual BERT
Multi-task support
Supports various natural language processing tasks such as text classification and named entity recognition
High-quality training data
Fine-tuned using multiple high-quality datasets including JW300, OPUS CC-Align, IGBO NLP corpus, and Igbo CC-100
Model Capabilities
Igbo text understanding
Masked language modeling
Named entity recognition
Text classification
Use Cases
Natural language processing
Igbo text classification
Performing classification tasks on Igbo text
Igbo named entity recognition
Identifying named entities in Igbo text
Achieved an F1 score of 86.75 on the MasakhaNER dataset
Featured Recommended AI Models