Abstract
The paper describes the development process of the Tilde’s NMT systems that were submitted for the WMT 2018 shared task on news translation. We describe the data filtering and pre-processing workflows, the NMT system training architectures, and automatic evaluation results. For the WMT 2018 shared task, we submitted seven systems (both constrained and unconstrained) for English-Estonian and Estonian-English translation directions. The submitted systems were trained using Transformer models.- Anthology ID:
- W18-6423
- Volume:
- Proceedings of the Third Conference on Machine Translation: Shared Task Papers
- Month:
- October
- Year:
- 2018
- Address:
- Belgium, Brussels
- Editors:
- Ondřej Bojar, Rajen Chatterjee, Christian Federmann, Mark Fishel, Yvette Graham, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Philipp Koehn, Christof Monz, Matteo Negri, Aurélie Névéol, Mariana Neves, Matt Post, Lucia Specia, Marco Turchi, Karin Verspoor
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 473–481
- Language:
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/W18-6423/
- DOI:
- 10.18653/v1/W18-6423
- Cite (ACL):
- Mārcis Pinnis, Matīss Rikters, and Rihards Krišlauks. 2018. Tilde’s Machine Translation Systems for WMT 2018. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 473–481, Belgium, Brussels. Association for Computational Linguistics.
- Cite (Informal):
- Tilde’s Machine Translation Systems for WMT 2018 (Pinnis et al., WMT 2018)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/W18-6423.pdf
- Data
- WMT 2018