Loading...
Loading...

Go to the content (press return)

The TALP-UPC machine translation systems for WMT18 news translation shared task

Author
Casas, N.; Escolano, C.; Ruiz, M.; Fonollosa, José A. R.
Type of activity
Presentation of work at congresses
Name of edition
3rd Conference on Machine Translation
Date of publication
2018
Presentation's date
2018-10-31
Book of congress proceedings
WMT2018: Third Conference on Machine Translation: proceedings of the conference: october 31-november 1, 2018, Brussels, Belgium
First page
359
Last page
364
Publisher
Association for Computational Linguistics
Repository
http://hdl.handle.net/2117/126757 Open in new window
URL
http://www.statmt.org/wmt18/pdf/WMT033.pdf Open in new window
Abstract
In this article we describe the TALP-UPC research group participation in the WMT18 news shared translation task for FinnishEnglish and Estonian-English within the multi-lingual subtrack. All of our primary submissions implement an attention-based Neural Machine Translation architecture. Given that Finnish and Estonian belong to the same language family and are similar, we use as training data the combination of the datasets of both language pairs to paliate the data scarceness of each individual...
Citation
Casas, N., Escolano, C., Ruiz, M., Fonollosa, J. A. R. The TALP-UPC machine translation systems for WMT18 news translation shared task. A: Conference on Machine Translation. "WMT2018: Third Conference on Machine Translation: proceedings of the conference: october 31-november 1, 2018, Brussels, Belgium". Stroudsburg, PA: Association for Computational Linguistics, 2018, p. 359-364.
Group of research
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center
TALP - Centre for Language and Speech Technologies and Applications
VEU - Speech Processing Group

Participants