Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Pytorch Language Models trained on South African Languages

Domain:

natural language processing

Record type:

model
Creator:
HayMesBuys, Jan
Publisher:
Uni
Host:avatar
Pytorch Language Models trained on the South African isiZulu and Sepedi languages using the NCHLT and Isolezwe datasets.
AWD-LSTM, QRNN and Basic LSTM architectures are each included for each of the datasets used.

Visit

doi.orgzivahub.uct.ac.za

Tasks

language modeling

Languages

Sotho, NorthernZulu

Tags

170203 Knowledge Representation and Machine LearningFOS: PsychologyFOS: Psychology

Licenses

MIT Licensehttps://opensource.org/licenses/MIT

Similar

AfroXLMR-Social: Adapting Pre-trained Language Models for African Languages Social Media TextAdapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-TuningAdvancing sentiment analysis for low-resourced african languages using pre-trained language modelsFig 5 - Advancing sentiment analysis for low-resourced african languages using pre-trained language modelsFig 4 - Advancing sentiment analysis for low-resourced african languages using pre-trained language modelsExplainable Pre-Trained Language Models for Sentiment Analysis in Low-Resourced Languages

AfroXLMR-Social: Adapting Pre-trained Language Models for African Languages Social Media Text

Language models built from various sources are the foundation of today's NLP progress. However, for

Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning

Multilingual pre-trained language models (PLMs) have demonstrated impressive performance on several downstream tasks for both high-resourced and low-resourced languages. However, there is still a large performance drop for languages unseen during pre-training, espe

Advancing sentiment analysis for low-resourced african languages using pre-trained language models

While sentiment analysis systems excel in high-resource languages, most African languages facing lim

Fig 5 - Advancing sentiment analysis for low-resourced african languages using pre-trained language models

Mean F1 scores of PLMs fine-tuned on closely related African languages, with 95% confidence inter

Fig 4 - Advancing sentiment analysis for low-resourced african languages using pre-trained language models

Mean F1 scores for all models with 95% confidence intervals across five African languages. The er

Explainable Pre-Trained Language Models for Sentiment Analysis in Low-Resourced Languages

Sentiment analysis is a pivotal tool for gauging the public’s perception and understanding