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.
@article{arxiv.1811.05909,
title = {The ADAPT System Description for the IWSLT 2018 Basque to English Translation Task},
author = {Alberto Poncelas and Andy Way and Kepa Sarasola},
journal= {arXiv preprint arXiv:1811.05909},
year = {2018}
}