Paper Info
Title
Microsoft's Submission to the WMT2018 News Translation Task: How I Learned to Stop Worrying and Love the Data.
Abstract
This paper describes the Microsoft submission to the WMT2018 news translation shared task. We participated in one language direction -- English-German. Our system follows current best-practice and combines state-of-the-art models with new data filtering (dual conditional cross-entropy filtering) and sentence weighting methods. We trained fairly standard Transformer-big models with an updated version of Edinburghu0027s training scheme for WMT2017 and experimented with different filtering schemes for Paracrawl. According to automatic metrics (BLEU) we reached the highest score for this subtask with a nearly 2 BLEU point margin over the next strongest system. Based on human evaluation we ranked first among constrained systems. We believe this is mostly caused by our data filtering/weighting regime.
Year
DOI
Venue
2018
10.18653/v1/w18-6415
WMT (shared task)
DocType
Volume
Citations 
Conference
abs/1809.00196
0
PageRank 
References 
Authors
0.34
0
1
Name
Order
Citations
PageRank
Marcin Junczys-Dowmunt131224.24