How Far Can 100 Samples Go? Unlocking Overall Zero-Shot Multilingual Translation via Tiny Multi-Parallel Data

arXiv:2401.12413v2 Announce Type: replace-cross
Abstract: Zero-shot translation aims to translate between language pairs not seen during training in Multilingual Machine Translation (MMT) and is largely considered an open problem. A common, albeit resource-consuming, solution is to add as many related translation directions as possible to the training corpus. In this paper, we show that for an English-centric model, surprisingly large zero-shot improvements can be achieved by simply fine-tuning with a very small amount of multi-parallel data. For example, on the …

abstract arxiv cs.cl cs.lg data language machine machine translation multilingual samples solution training translate translation type via zero-shot