Towards Neural Machine Translation for African Languages
This addresses the need for inclusive online education in South Africa by improving translation for low-resourced local languages, though it is incremental as it applies existing NMT techniques to a new domain.
The paper tackled the problem of machine translation for low-resourced African languages, specifically English-to-Setswana, and achieved state-of-the-art performance with a 5.33 BLEU point improvement using the Transformer architecture.
Given that South African education is in crisis, strategies for improvement and sustainability of high-quality, up-to-date education must be explored. In the migration of education online, inclusion of machine translation for low-resourced local languages becomes necessary. This paper aims to spur the use of current neural machine translation (NMT) techniques for low-resourced local languages. The paper demonstrates state-of-the-art performance on English-to-Setswana translation using the Autshumato dataset. The use of the Transformer architecture beat previous techniques by 5.33 BLEU points. This demonstrates the promise of using current NMT techniques for African languages.