Bert Base Multilingual Cased Finetuned Naija

🚀 bert-base-multilingual-cased-finetuned-naija

This is a Nigerian-Pidgin BERT model fine-tuned from bert-base-multilingual-cased, offering better performance in named entity recognition than multilingual BERT.

🚀 Quick Start

This model can be used with the Transformers pipeline for masked token prediction.

>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='Davlan/bert-base-multilingual-cased-finetuned-naija')
>>> unmasker("Another attack on ambulance happen for Koforidua in March [MASK] year where robbers kill Ambulance driver")

✨ Features

bert-base-multilingual-cased-finetuned-naija is a Nigerian-Pidgin BERT model. It is obtained by fine-tuning the bert-base-multilingual-cased model on Nigerian-Pidgin language texts, and provides better performance than the multilingual BERT on named entity recognition datasets.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

>>> from transformers import pipeline
>>> unmasker = pipeline('fill-mask', model='Davlan/bert-base-multilingual-cased-finetuned-naija')
>>> unmasker("Another attack on ambulance happen for Koforidua in March [MASK] year where robbers kill Ambulance driver")

📚 Documentation

Intended uses & limitations

How to use

You can use this model with Transformers pipeline for masked token prediction. The example code is shown above in the "Quick Start" section.

Limitations and bias

This model is limited by its training dataset of entity-annotated news articles from a specific span of time. This may not generalize well for all use cases in different domains.

Training data

This model was fine-tuned on JW300 + BBC Pidgin

Training procedure

This model was trained on a single NVIDIA V100 GPU

Eval results on Test set (F-score, average over 5 runs)

BibTeX entry and citation info

By David Adelani