Small Data? No Problem: Exploring the Viability of Multilingual Pretrained Language Models for Low-resourced Languages

Pretrained multilingual language models have been shown to work well on many languages for a variety of downstream NLP tasks. However, these models are known to require a lot of training data. This consequently leaves out a huge percentage of the world's languages as they are under-resourced. Furthermore, a major motivation behind these models is that lower-resource languages benefit from joint training with higher-resource languages. In this work, we challenge this assumption and present the first attempt at training a multilingual language model on only low-resource languages. We show that it is possible to train competitive multilingual language models on less than 1 GB of text. Our model, named AfriBERTa, covers 11 African languages, including the first language model for 4 of these languages. Evaluations on named entity recognition and text classification spanning 10 languages show that our model outperforms mBert and XLM-R in several languages and is very competitive overall. Results suggest that our ``small data'' approach based on similar languages may sometimes work better than joint training on large datasets with high-resource languages. Code, data and models are released at github.com .