The ADAPT system description for the IWSLT 2018 Basque to English
translation task
Poncelas, AlbertoORCID: 0000-0002-5089-1687, Way, AndyORCID: 0000-0001-5736-5930 and Sarasola, Kepa
(2018)
The ADAPT system description for the IWSLT 2018 Basque to English
translation task.
In: IWSLT 2018 - 15th International Workshop on Spoken Language Translation, 29-30 Oct 2018, Bruges, Belgium.
In this paper we present the ADAPT system built for the
Basque to English Low Resource MT Evaluation Campaign.
Basque is a low-resourced, morphologically-rich language.
This poses a challenge for Neural Machine Translation models which usually achieve better performance when trained
with large sets of data.
Accordingly, we used synthetic data to improve the translation quality produced by a model built using only authentic
data. Our proposal uses back-translated data to: (a) create
new sentences, so the system can be trained with more data;
and (b) translate sentences that are close to the test set, so the
model can be fine-tuned to the document to be translated.
This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:
TADEEP project (Spanish Ministry of Economy and Competitiveness TIN2015-70214-P, with FEDER funding), ADAPT Centre for Digital Content Technology which is funded under the SFI Research Centres Programme (Grant 13/RC/2106) and is co-funded under the European Regional Development Fund
ID Code:
23199
Deposited On:
24 Apr 2019 12:26 by
Thomas Murtagh
. Last Modified 22 Jan 2021 14:20