CUNI Systems in WMT21: Revisiting Backtranslation Techniques for English-Czech NMT
2021-11-01WMT (EMNLP) 2021Unverified0· sign in to hype
Petr Gebauer, Ondřej Bojar, Vojtěch Švandelík, Martin Popel
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
We describe our two NMT systems submitted to the WMT2021 shared task in English-Czech news translation: CUNI-DocTransformer (document-level CUBBITT) and CUNI-Marian-Baselines. We improve the former with a better sentence-segmentation pre-processing and a post-processing for fixing errors in numbers and units. We use the latter for experiments with various backtranslation techniques.