Tilde’s Machine Translation Systems for WMT 2018

Mārcis Pinnis, Matīss Rikters, Rihards Krišlauks


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
Venues:
EMNLP | WMT | WS
SIG:
SIGMT
Publisher:
Association for Computational Linguistics
Note:
Pages:
473–481
Language:
URL:
https://www.aclweb.org/anthology/W18-6423
DOI:
10.18653/v1/W18-6423
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W18-6423.pdf