Investigating Multi-Pivot Ensembling with Massively Multilingual Machine Translation Models

arXiv:2311.07439v3 Announce Type: replace-cross
Abstract: Massively multilingual machine translation models allow for the translation of a large number of languages with a single model, but have limited performance on low- and very-low-resource translation directions. Pivoting via high-resource languages remains a strong strategy for low-resource directions, and in this paper we revisit ways of pivoting through multiple languages. Previous work has used a simple averaging of probability distributions from multiple paths, but we find that this performs worse than using a …

abstract arxiv cs.ai cs.cl cs.lg languages low machine machine translation massively multilingual multilingual paper performance pivot pivoting strategy translation type via