Skip to content
conftrace_
2019 ACL ACL 2019

UdS-DFKI Participation at WMT 2019: Low-Resource (en-gu) and Coreference-Aware (en-de) Systems

Abstract

AbstractThis paper describes the UdS-DFKI submission to the WMT2019 news translation task for Gujarati–English (low-resourced pair) and German–English (document-level evaluation). Our systems rely on the on-line extraction of parallel sentences from comparable corpora for the first scenario and on the inclusion of coreference-related information in the training data in the second one.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing
🐣 Hot Topic Early Bird - low-resource language

Authors

Cristina España-Bonet, Dana Ruiter

Topics

Natural Language Processing > Understanding > Coreference Resolution Natural Language Processing > Applications > Machine Translation Machine Learning > Learning Types > Multi-Lingual Learning

Keywords

neural machine translation document-level translation coreference resolution low-resource language low-resource machine translation comparable corpus comparable corpus mining parallel sentence extraction
Download PDF

More from ACL 2019

All ACL 2019 papers →
Kyoto University Participation to the WMT 2019 News Shared Task
NICT’s Supervised Neural Machine Translation Systems for the WMT19 News Translation Task
The University of Sydney’s Machine Translation System for WMT19
The IIIT-H Gujarati-English Machine Translation System for WMT19
Kingsoft’s Neural Machine Translation System for WMT19
The AFRL WMT19 Systems: Old Favorites and New Tricks