CUNI Systems in WMT21: Revisiting Backtranslation Techniques for English-Czech NMT

27788

Authors

nan

Abstract

AbstractWe 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.

Keywords

nan

Full Content

nan

Labeled Text

AbstractWe 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.

Publication Details

Paper ID:
27788
Year:
2021
Publication:
TIPSTER
Publication Type:
conf
DOI:
nan