Grant Erdmann
YOU?
Author Swipe
View article: The AFRL WMT19 Systems: Old Favorites and New Tricks
The AFRL WMT19 Systems: Old Favorites and New Tricks Open
This 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 t…
View article: Quality and Coverage: The AFRL Submission to the WMT19 Parallel Corpus Filtering for Low-Resource Conditions Task
Quality and Coverage: The AFRL Submission to the WMT19 Parallel Corpus Filtering for Low-Resource Conditions Task Open
The WMT19 Parallel Corpus Filtering For Low-Resource Conditions Task aims to test various methods of filtering a noisy parallel corpora, to make them useful for training machine translation systems. This year the noisy corpora are the rela…
View article: The AFRL WMT18 Systems: Ensembling, Continuation and Combination
The AFRL WMT18 Systems: Ensembling, Continuation and Combination Open
This paper describes the Air Force Research Laboratory (AFRL) machine translation systems and the improvements that were developed during the WMT18 evaluation campaign. This year, we examined the developments and additions to popular neura…
View article: The AFRL-Ohio State WMT18 Multimodal System: Combining Visual with Traditional
The AFRL-Ohio State WMT18 Multimodal System: Combining Visual with Traditional Open
AFRL-Ohio State extends its usage of visual domain-driven machine translation for use as a peer with traditional machine translation systems. As a peer, it is enveloped into a system combination of neural and statistical MT systems to pres…
View article: Coverage and Cynicism: The AFRL Submission to the WMT 2018 Parallel Corpus Filtering Task
Coverage and Cynicism: The AFRL Submission to the WMT 2018 Parallel Corpus Filtering Task Open
The WMT 2018 Parallel Corpus Filtering Task aims to test various methods of filtering a noisy parallel corpus, to make it useful for training machine translation systems. We describe the AFRL submissions, including their preprocessing meth…
View article: The AFRL WMT17 Neural Machine Translation Training Task Submission
The AFRL WMT17 Neural Machine Translation Training Task Submission Open
The WMT17 Neural Machine Translation Training Task aims to test various methods of training neural machine translation systems.We describe the AFRL submission, including preprocessing and its knowledge distillation framework.Teacher system…
View article: The AFRL-MITLL WMT17 Systems: Old, New, Borrowed, BLEU
The AFRL-MITLL WMT17 Systems: Old, New, Borrowed, BLEU Open
This paper describes the AFRL-MITLL machine translation systems and the improvements that were developed during the WMT17 evaluation campaign.This year, we explore the continuing proliferation of Neural Machine Translation toolkits, revisi…
View article: The AFRL-MITLL WMT16 News-Translation Task Systems
The AFRL-MITLL WMT16 News-Translation Task Systems Open
Jeremy Gwinnup, Tim Anderson, Grant Erdmann, Katherine Young, Michaeel Kazi, Elizabeth Salesky, Brian Thompson. Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers. 2016.