Natural language processing for African languages
–arXiv.org Artificial Intelligence
Recent advances in word embeddings and language models use large-scale, unlabelled data and self-supervised learning to boost NLP performance. Multilingual models, often trained on web-sourced data like Wikipedia, face challenges: few low-resource languages are included, their data is often noisy, and lack of labeled datasets makes it hard to evaluate performance outside high-resource languages like English. In this dissertation, we focus on languages spoken in Sub-Saharan Africa where all the indigenous languages in this region can be regarded as low-resourced in terms of the availability of labelled data for NLP tasks and unlabelled data found on the web. We analyse the noise in the publicly available corpora, and curate a high-quality corpus, demonstrating that the quality of semantic representations learned in word embeddings does not only depend on the amount of data but on the quality of pre-training data. We demonstrate empirically the limitations of word embeddings, and the opportunities the multilingual pre-trained language model (PLM) offers especially for languages unseen during pre-training and low-resource scenarios. We further study how to adapt and specialize multilingual PLMs to unseen African languages using a small amount of monolingual texts. To address the under-representation of the African languages in NLP research, we developed large scale human-annotated labelled datasets for 21 African languages in two impactful NLP tasks: named entity recognition and machine translation. We conduct an extensive empirical evaluation using state-of-the-art methods across supervised, weakly-supervised, and transfer learning settings.
arXiv.org Artificial Intelligence
Jul-2-2025
- Country:
- Asia > Middle East (0.92)
- North America > United States
- California (0.45)
- Minnesota (0.28)
- Europe
- Germany (0.67)
- United Kingdom > England (0.27)
- Africa
- Middle East (1.00)
- Nigeria (0.93)
- Genre:
- Research Report > New Finding (1.00)
- Industry:
- Media > News (1.00)
- Information Technology (1.00)
- Government > Regional Government (1.00)
- Education (1.00)
- Law (0.92)
- Energy (0.92)
- Leisure & Entertainment > Sports (0.67)
- Health & Medicine > Therapeutic Area
- Infections and Infectious Diseases (0.67)
- Immunology (0.67)
- Technology:
- Information Technology > Artificial Intelligence
- Natural Language
- Text Processing (1.00)
- Machine Translation (1.00)
- Large Language Model (1.00)
- Chatbot (1.00)
- Machine Learning
- Statistical Learning (1.00)
- Neural Networks > Deep Learning (1.00)
- Inductive Learning (1.00)
- Natural Language
- Information Technology > Artificial Intelligence