Skip to main navigation Skip to search Skip to main content

Tilde at WMT 2020: News Task Systems

  • Tilde Company
  • University of Latvia

Research output: Chapter in Book/Report/Conference proceedingConference paperResearchpeer-review

2 Citations (Scopus)

Abstract

This paper describes Tilde's submission to the WMT2020 shared task on news translation for both directions of the English↔Polish language pair in both the constrained and the unconstrained tracks. We follow our submissions form the previous years and build our baseline systems to be morphologically motivated sub-word unit-based Transformer base models that we train using the Marian machine translation toolkit. Additionally, we experiment with different parallel and monolingual data selection schemes, as well as sampled backtranslation. Our final models are ensembles of Transformer base and Transformer big models which feature right-to-left re-ranking.

Original languageEnglish
Title of host publication5th Conference on Machine Translation Wmt 2020 Proceedings
EditorsLoic Barrault, Ondrej Bojar, Fethi Bougares, Rajen Chatterjee, Marta R. Costa-Jussa, Christian Federmann, Mark Fishel, Alexander Fraser, Yvette Graham, Paco Guzman, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Andre Martins, Makoto Morishita, Christof Monz, Masaaki Nagata, Toshiaki Nakazawa, Matteo Negri
Place of Publication[Stroudsburg]
PublisherAssociation for Computational Linguistics
Pages175-180
ISBN (Print)9781948087810
Publication statusPublished - 2020

Publication series

Name5th Conference on Machine Translation, WMT 2020 - Proceedings

OECD Field of Science

  • 1.2 Computer and Information Sciences

Fingerprint

Dive into the research topics of 'Tilde at WMT 2020: News Task Systems'. Together they form a unique fingerprint.

Cite this