In this article we describe the TALP-UPC research group participation in the WMT18 news shared translation task for Finnish-English 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 pair. We also report the translation quality of systems trained on individual language pair data to serve as baseline and comparison reference.
Noe Casas, Carlos Escolano, Marta R. Costa-jussà, and José A. R. Fonollosa. 2018. The TALP-UPC Machine Translation Systems for WMT18 News Shared Translation Task. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 355–360, Belgium, Brussels. Association for Computational Linguistics.
@inproceedings{casas-etal-2018-talp,
title = "The {TALP}-{UPC} Machine Translation Systems for {WMT}18 News Shared Translation Task",
author = "Casas, Noe and
Escolano, Carlos and
Costa-juss{\`a}, Marta R. and
Fonollosa, Jos{\'e} A. R.",
editor = "Bojar, Ond{\v{r}}ej and
Chatterjee, Rajen and
Federmann, Christian and
Fishel, Mark and
Graham, Yvette and
Haddow, Barry and
Huck, Matthias and
Yepes, Antonio Jimeno and
Koehn, Philipp and
Monz, Christof and
Negri, Matteo and
N{\'e}v{\'e}ol, Aur{\'e}lie and
Neves, Mariana and
Post, Matt and
Specia, Lucia and
Turchi, Marco and
Verspoor, Karin",
booktitle = "Proceedings of the Third Conference on Machine Translation: Shared Task Papers",
month = oct,
year = "2018",
address = "Belgium, Brussels",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-6406/",
doi = "10.18653/v1/W18-6406",
pages = "355--360",
abstract = "In this article we describe the TALP-UPC research group participation in the WMT18 news shared translation task for Finnish-English 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 pair. We also report the translation quality of systems trained on individual language pair data to serve as baseline and comparison reference."
}
%0 Conference Proceedings
%T The TALP-UPC Machine Translation Systems for WMT18 News Shared Translation Task
%A Casas, Noe
%A Escolano, Carlos
%A Costa-jussà, Marta R.
%A Fonollosa, José A. R.
%Y Bojar, Ondřej
%Y Chatterjee, Rajen
%Y Federmann, Christian
%Y Fishel, Mark
%Y Graham, Yvette
%Y Haddow, Barry
%Y Huck, Matthias
%Y Yepes, Antonio Jimeno
%Y Koehn, Philipp
%Y Monz, Christof
%Y Negri, Matteo
%Y Névéol, Aurélie
%Y Neves, Mariana
%Y Post, Matt
%Y Specia, Lucia
%Y Turchi, Marco
%Y Verspoor, Karin
%S Proceedings of the Third Conference on Machine Translation: Shared Task Papers
%D 2018
%8 October
%I Association for Computational Linguistics
%C Belgium, Brussels
%F casas-etal-2018-talp
%X In this article we describe the TALP-UPC research group participation in the WMT18 news shared translation task for Finnish-English 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 pair. We also report the translation quality of systems trained on individual language pair data to serve as baseline and comparison reference.
%R 10.18653/v1/W18-6406
%U https://aclanthology.org/W18-6406/
%U https://doi.org/10.18653/v1/W18-6406
%P 355-360
Noe Casas, Carlos Escolano, Marta R. Costa-jussà, and José A. R. Fonollosa. 2018. The TALP-UPC Machine Translation Systems for WMT18 News Shared Translation Task. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 355–360, Belgium, Brussels. Association for Computational Linguistics.