MMTAfrica: Multilingual Machine Translation for African Languages
Domain:
natural language processingRecord type:
paper
In this paper, we focus on the task of multilingual machine translation for African languages and describe our contribution in the 2021 WMT Shared Task: Large-Scale Multilingual Machine Translation. We introduce MMTAfrica, the first many-to-many multilingual translation system for six African languages: Fon (fon), Igbo (ibo), Kinyarwanda (kin), Swahili/Kiswahili (swa), Xhosa (xho), and Yoruba (yor) and two non-African languages: English (eng) and French (fra). For multilingual translation concerning African languages, we introduce a novel backtranslation and reconstruction objective, BT&REC, inspired by the random online back translation and T5 modelling framework respectively, to effectively leverage monolingual data. Additionally, we report improvements from MMTAfrica over the FLORES 101 benchmarks (spBLEU gains ranging from +0.58 in Swahili to French to +19.46 in French to Xhosa).
Similar
MMTAfrica: Multilingual Machine Translation for African LanguagesANVITA-African: A Multilingual Neural Machine Translation System for African LanguagesTencent's Multilingual Machine Translation System for WMT22 Large-Scale African LanguagesMultilingual Neural Machine Translation for Zero-Resource LanguagesMultilingual Neural Machine Translation for Low Resource Languages