Open-source Model: xlm-roberta-base-finetuned-luganda - Accurately Identify Luganda Named Entities

Home

Xlm Roberta Base Finetuned Luganda

Developed by Davlan

A model fine-tuned on Luganda text based on XLM-RoBERTa, outperforming the base model in Named Entity Recognition tasks

Large Language Model

Transformers

#Luganda NLP #Multilingual fine-tuning #Named Entity Recognition optimization

Downloads 23

Release Time : 3/2/2022

Model Overview

This model is a Luganda RoBERTa obtained by fine-tuning xlm-roberta-base on a Luganda corpus, specifically optimized for Named Entity Recognition performance

Model Features

Luganda optimization

Specifically fine-tuned for Luganda, providing better language understanding capabilities

Enhanced Named Entity Recognition

Outperforms the base XLM-RoBERTa model on NER tasks

Multilingual foundation

Based on the powerful multilingual XLM-RoBERTa architecture

Model Capabilities

Luganda text understanding

Named Entity Recognition

Masked language prediction

Use Cases

Natural Language Processing

Luganda text analysis

Used for processing and analyzing Luganda text content

Better recognition accuracy compared to the base model

Named Entity Recognition

Identifying entities such as person names and locations in Luganda text

Provides optimized recognition performance

🚀 xlm-roberta-base-finetuned-luganda

The xlm-roberta-base-finetuned-luganda is a Luganda RoBERTa model, which offers better performance in named entity recognition compared to the XLM-RoBERTa model.

🚀 Quick Start

The xlm-roberta-base-finetuned-luganda is a Luganda RoBERTa model. It is derived by fine - tuning the xlm - roberta - base model on Luganda language texts. This model demonstrates better performance than the XLM - RoBERTa on named entity recognition datasets.

Specifically, it is a xlm - roberta - base model fine - tuned on the Luganda corpus.

✨ Features

Intended uses & limitations

How to use

You can utilize this model with the Transformers pipeline for masked token prediction.

>>> from transformers import pipeline
>>> unmasker = pipeline('fill - mask', model='Davlan/xlm - roberta - base - finetuned - luganda')
>>> unmasker("Ffe tulwanyisa abo abaagala okutabangula <mask>, Kimuli bwe yategeezezza.")

Limitations and bias

This model is restricted by its training dataset, which consists of entity - annotated news articles from a specific time frame. As a result, it may not perform well across all use cases in different domains.

📦 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/xlm - roberta - base - finetuned - luganda')
>>> unmasker("Ffe tulwanyisa abo abaagala okutabangula <mask>, Kimuli bwe yategeezezza.")

📚 Documentation

Training data

This model was fine - tuned on JW300 + [BUKKEDDE](https://github.com/masakhane - io/masakhane - ner/tree/main/text_by_language/luganda) +[Luganda CC - 100](http://data.statmt.org/cc - 100/)

Training procedure

This model was trained on a single NVIDIA V100 GPU

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

Dataset	XLM - R F1	lg_roberta F1
[MasakhaNER](https://github.com/masakhane - io/masakhane - ner)	79.69	84.70

BibTeX entry and citation info

By David Adelani

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