# Investigating an approach for low resource language dataset creation, curation and classification: Setswana and Sepedi

arXiv: https://arxiv.org/abs/2003.04986 · HTML: https://mlsanity.com/paper/2003.04986/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Feb 2020.

## Built on by (most cited first, 15 of 15)

- [MASSIVE: A 1M-Example Multilingual Natural Language Understanding Dataset with 51 Typologically-Diverse Languages](https://mlsanity.com/paper/2204.08582/) (2022)
- [Building Machine Translation Systems for the Next Thousand Languages](https://mlsanity.com/paper/2205.03983/) (2022)
- [Listening to Affected Communities to Define Extreme Speech: Dataset and Experiments](https://mlsanity.com/paper/2203.11764/) (2022)
- [Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead](https://mlsanity.com/paper/2505.21315/) (2025)
- [Preparing the Vuk'uzenzele and ZA-gov-multilingual South African multilingual corpora](https://mlsanity.com/paper/2303.03750/) (2023)
- [SMOL: Professionally translated parallel data for 115 under-represented languages](https://mlsanity.com/paper/2502.12301/) (2025)
- [Kencorpus: A Kenyan Language Corpus of Swahili, Dholuo and Luhya for Natural Language Processing Tasks](https://mlsanity.com/paper/2208.12081/) (2022)
- [Socially Responsible Data for Large Multilingual Language Models](https://mlsanity.com/paper/2409.05247/) (2024)
- [PuoBERTa: Training and evaluation of a curated language model for Setswana](https://mlsanity.com/paper/2310.09141/) (2023)
- [Training Cross-Lingual embeddings for Setswana and Sepedi](https://mlsanity.com/paper/2111.06230/) (2021)
- [LR-Sum: Summarization for Less-Resourced Languages](https://mlsanity.com/paper/2212.09674/) (2022)
- [Izindaba-Tindzaba: Machine learning news categorisation for Long and Short Text for isiZulu and Siswati](https://mlsanity.com/paper/2306.07426/) (2023)
- [Pula: Training Large Language Models for Setswana](https://mlsanity.com/paper/2408.02239/) (2024)
- [Building Representative Corpora from Illiterate Communities: A Review of Challenges and Mitigation Strategies for Developing Countries](https://mlsanity.com/paper/2102.02841/) (2021)
- [The Influence of Iconicity in Transfer Learning for Sign Language Recognition](https://mlsanity.com/paper/2603.03316/) (2026)

## Abstract (arXiv)

The recent advances in Natural Language Processing have been a boon for well-represented languages in terms of available curated data and research resources. One of the challenges for low-resourced languages is clear guidelines on the collection, curation and preparation of datasets for different use-cases. In this work, we take on the task of creation of two datasets that are focused on news headlines (i.e short text) for Setswana and Sepedi and creation of a news topic classification task. We document our work and also present baselines for classification. We investigate an approach on data augmentation, better suited to low resource languages, to improve the performance of the classifiers