Tilde's Machine Translation Systems for WMT 2018
2018-10-01WS 2018Code Available0· sign in to hype
M{\=a}rcis Pinnis, Mat{\=\i}ss Rikters, Rihards Kri{\v{s}}lauks
Code Available — Be the first to reproduce this paper.
ReproduceCode
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.