Transformers for Low-resource Neural Machine Translation

Andargachew Gezmu, Andreas Nürnberger

2022

Abstract

The recent advances in neural machine translation enable it to be state-of-the-art. However, although there are significant improvements in neural machine translation for a few high-resource languages, its performance is still low for less-resourced languages as the amount of training data significantly affects the quality of the machine translation models. Therefore, identifying a neural machine translation architecture that can train the best models in low-data conditions is essential for less-resourced languages. This research modified the Transformer-based neural machine translation architectures for low-resource polysynthetic languages. Our proposed system outperformed the strong baseline in the automatic evaluation of the experiments on the public benchmark datasets.

Paper Citation

in Harvard Style

Gezmu A. and Nürnberger A. (2022). Transformers for Low-resource Neural Machine Translation. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI, ISBN 978-989-758-547-0, pages 459-466. DOI: 10.5220/0010971500003116

in Bibtex Style

@conference{nlpinai22,
author={Andargachew Gezmu and Andreas Nürnberger},
title={Transformers for Low-resource Neural Machine Translation},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI,},
year={2022},
pages={459-466},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010971500003116},
isbn={978-989-758-547-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI,
TI - Transformers for Low-resource Neural Machine Translation
SN - 978-989-758-547-0
AU - Gezmu A.
AU - Nürnberger A.
PY - 2022
SP - 459
EP - 466
DO - 10.5220/0010971500003116