Towards Neural Machine Translation for African Languages

Abstract

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.

References in corpus (3)

• Convolutional Sequence to Sequence Learning
• Universal Neural Machine Translation for Extremely Low Resource Languages
• Meta-Learning for Low-Resource Neural Machine Translation

Cited by in corpus (8)

• A Focus on Neural Machine Translation for African Languages
• On Optimal Transformer Depth for Low-Resource Language Translation
• Towards Supervised and Unsupervised Neural Machine Translation Baselines for Nigerian Pidgin
• Low-Resource Neural Machine Translation for Southern African Languages
• Benchmarking Neural Machine Translation for Southern African Languages
• OkwuGbé: End-to-End Speech Recognition for Fon and Igbo
• Short Text Language Identification for Under Resourced Languages
• Crowdsourced Phrase-Based Tokenization for Low-Resourced Neural Machine Translation: The Case of Fon Language