Answers are grounded in this paper and cite their sources.
Transfer learning or multilingual model is essential for low-resource neural machine translation (NMT), but the applicability is limited to cognate languages by sharing their vocabularies. This paper shows effective techniques to transfer a pre-trained NMT model to a new, unrelated language without shared vocabularies.
No takes yet. Share an insight, caveat, or question.
Kim et al. (2019) studied this question.