Masakhane NMT

Masakhane is an research effort for NLP for African languages that is OPEN SOURCE, CONTINENT-WIDE, DISTRIBUTED and ONLINE. The initiave repository houses the data, code, results and research for building open baseline NLP results for African languages. I contributed to the project with gathering parallel data in Modern Standard Arabic and modeling it using Joeynmt transformer based library. The team had an accepted submission in Africa4NLP workshop at ICLR'20 and also submitted to EMNLP'20. link to github repo.