Skip to content
conftrace_
2018 EMNLP EMNLP 2018

The University of Edinburgh’s Submissions to the WMT18 News Translation Task

Abstract

AbstractThe University of Edinburgh made submissions to all 14 language pairs in the news translation task, with strong performances in most pairs. We introduce new RNN-variant, mixed RNN/Transformer ensembles, data selection and weighting, and extensions to back-translation.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing
🐣 Hot Topic Early Bird - data selection

Authors

Barry Haddow, Nikolay Bogoychev, Denis Emelin, Ulrich Germann, Roman Grundkiewicz, Kenneth Heafield, Antonio Valerio Miceli Barone, Rico Sennrich

Topics

Deep Learning > Architectures > Transformers Natural Language Processing > Applications > Machine Translation Deep Learning > Learning Types > Ensemble Learning

Keywords

ensemble learning neural machine translation ensemble method data selection
Download PDF

More from EMNLP 2018

All EMNLP 2018 papers →
The RWTH Aachen University English-German and German-English Unsupervised Neural Machine Translation Systems for WMT 2018
Cognate-aware morphological segmentation for multilingual neural translation
The AFRL WMT18 Systems: Ensembling, Continuation and Combination
TencentFmRD Neural Machine Translation for WMT18
The MLLP-UPV German-English Machine Translation System for WMT18
Microsoft’s Submission to the WMT2018 News Translation Task: How I Learned to Stop Worrying and Love the Data