FFR v1.1: Fon-French Neural Machine Translation
This work addresses language barriers for speakers and researchers of Fon, an incremental step in low-resource NMT.
The paper tackles the challenge of building a neural machine translation system for Fon, a low-resource and tonal African language, to French, resulting in the creation of the FFR v1.1 model and a publicly available dataset.
All over the world and especially in Africa, researchers are putting efforts into building Neural Machine Translation (NMT) systems to help tackle the language barriers in Africa, a continent of over 2000 different languages. However, the low-resourceness, diacritical, and tonal complexities of African languages are major issues being faced. The FFR project is a major step towards creating a robust translation model from Fon, a very low-resource and tonal language, to French, for research and public use. In this paper, we introduce FFR Dataset, a corpus of Fon-to-French translations, describe the diacritical encoding process, and introduce our FFR v1.1 model, trained on the dataset. The dataset and model are made publicly available at https://github.com/ bonaventuredossou/ffr-v1, to promote collaboration and reproducibility.