2000 character limit reached
Miðeind's WMT 2021 submission (2109.07343v1)
Published 15 Sep 2021 in cs.CL
Abstract: We present Mi{\dh}eind's submission for the English$\to$Icelandic and Icelandic$\to$English subsets of the 2021 WMT news translation task. Transformer-base models are trained for translation on parallel data to generate backtranslations iteratively. A pretrained mBART-25 model is then adapted for translation using parallel data as well as the last backtranslation iteration. This adapted pretrained model is then used to re-generate backtranslations, and the training of the adapted model is continued.
- Haukur Barri Símonarson (4 papers)
- Vésteinn Snæbjarnarson (13 papers)
- Pétur Orri Ragnarsson (3 papers)
- Haukur Páll Jónsson (3 papers)
- Vilhjálmur Þorsteinsson (3 papers)