Skip to content
conftrace_
2019 ACL ACL 2019

University of Tartu’s Multilingual Multi-domain WMT19 News Translation Shared Task Submission

Abstract

AbstractThis paper describes the University of Tartu’s submission to the news translation shared task of WMT19, where the core idea was to train a single multilingual system to cover several language pairs of the shared task and submit its results. We only used the constrained data from the shared task. We describe our approach and its results and discuss the technical issues we faced.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing
🐣 Hot Topic Early Bird - multilingual translation

Authors

Andre Tättar, Elizaveta Korotkova, Mark Fishel

Topics

Natural Language Processing > Applications > Machine Translation Natural Language Processing > Resources & Methods > Multilingual NLP Deep Learning > Learning Types > Transfer Learning Machine Learning > Learning Types > Multi-Lingual Learning

Keywords

transfer learning multilingual translation neural machine translation multi-domain translation news translation multilingual system constrained data
Download PDF

More from ACL 2019

All ACL 2019 papers →
The Universitat d’Alacant Submissions to the English-to-Kazakh News Translation Task at WMT 2019
CUED@WMT19:EWC&LMs
Baidu Neural Machine Translation Systems for WMT19
Neural Machine Translation for English–Kazakh with Morphological Segmentation and Synthetic Data
The LMU Munich Unsupervised Machine Translation System for WMT19
Combining Local and Document-Level Context: The LMU Munich Neural Machine Translation System at WMT19