EdinSaar@WMT21: North-Germanic Low-Resource Multilingual NMT
2021-09-29WMT (EMNLP) 2021Unverified0· sign in to hype
Svetlana Tchistiakova, Jesujoba Alabi, Koel Dutta Chowdhury, Sourav Dutta, Dana Ruiter
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
We describe the EdinSaar submission to the shared task of Multilingual Low-Resource Translation for North Germanic Languages at the Sixth Conference on Machine Translation (WMT2021). We submit multilingual translation models for translations to/from Icelandic (is), Norwegian-Bokmal (nb), and Swedish (sv). We employ various experimental approaches, including multilingual pre-training, back-translation, fine-tuning, and ensembling. In most translation directions, our models outperform other submitted systems.