Skip to content
conftrace_
2019 ACL ACL 2019

UdS Submission for the WMT 19 Automatic Post-Editing Task

Abstract

AbstractIn this paper, we describe our submission to the English-German APE shared task at WMT 2019. We utilize and adapt an NMT architecture originally developed for exploiting context information to APE, implement this in our own transformer model and explore joint training of the APE task with a de-noising encoder.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Hongfei Xu, Qiuhui Liu, Josef van Genabith

Topics

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

Keywords

neural machine translation automatic post-editing joint training context information context encoding transformer model denoising encoder
Download PDF

More from ACL 2019

All ACL 2019 papers →
USAAR-DFKI – The Transference Architecture for English–German Automatic Post-Editing
APE through Neural and Statistical MT with Augmented Data. ADAPT/DCU Submission to the WMT 2019 APE Shared Task
Effort-Aware Neural Automatic Post-Editing
Terminology-Aware Segmentation and Domain Feature for the WMT19 Biomedical Translation Task
Exploring Transfer Learning and Domain Data Selection for the Biomedical Translation
Huawei’s NMT Systems for the WMT 2019 Biomedical Translation Task