Multilingual transfer techniques often improve low-resource machine translation (MT). Many of these techniques are applied without considering data characteristics. We show in the context of Haitian-to-English translation that transfer effectiveness is correlated with amount of training data and relationships between knowledge-sharing languages. Our experiments suggest that for some languages beyond a threshold of authentic data, back-translation augmentation methods are counterproductive, while cross-lingual transfer from a sufficiently related language is preferred. We complement this finding by contributing a rule-based French-Haitian orthographic and syntactic engine and a novel method for phonological embedding. When used with multilingual techniques, orthographic transformation makes statistically significant improvements over conventional methods. And in very low-resource Jamaican MT, code-switching with a transfer language for orthographic resemblance yields a 6.63 BLEU point advantage.
@article{arxiv.2209.06295,
title = {Data-adaptive Transfer Learning for Translation: A Case Study in Haitian and Jamaican},
author = {Nathaniel R. Robinson and Cameron J. Hogan and Nancy Fulda and David R. Mortensen},
journal= {arXiv preprint arXiv:2209.06295},
year = {2022}
}