Skip to content
conftrace_
2019 ACL ACL 2019

The AFRL WMT19 Systems: Old Favorites and New Tricks

Abstract

AbstractThis paper describes the Air Force Research Laboratory (AFRL) machine translation systems and the improvements that were developed during the WMT19 evaluation campaign. This year, we refine our approach to training popular neural machine translation toolkits, experiment with a new domain adaptation technique and again measure improvements in performance on the Russian–English language pair.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing
🐣 Hot Topic Early Bird - model ensemble

Authors

Jeremy Gwinnup, Grant Erdmann, Tim Anderson

Topics

Machine Learning > Application Areas > Domain Adaptation Deep Learning > Architectures > Transformers Natural Language Processing > Applications > Machine Translation Deep Learning > Learning Types > Transfer Learning

Keywords

domain adaptation neural machine translation model ensemble data filtering russian-english translation neural machine translation toolkit
Download PDF

More from ACL 2019

All ACL 2019 papers →
UdS-DFKI Participation at WMT 2019: Low-Resource (en-gu) and Coreference-Aware (en-de) Systems
The IIIT-H Gujarati-English Machine Translation System for WMT19
Kingsoft’s Neural Machine Translation System for WMT19
Evaluating the Supervised and Zero-shot Performance of Multi-lingual Translation Models
The MLLP-UPV Supervised Machine Translation Systems for WMT19 News Translation Task
Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation