Neural Machine Translation for Amharic-English Translation

Andargachew Gezmu, Andreas Nürnberger, Tesfaye Bati

2021

Abstract

This paper describes neural machine translation between orthographically and morphologically divergent languages. Amharic has a rich morphology; it uses the syllabic Ethiopic script. We used a new transliteration technique for Amharic to facilitate vocabulary sharing. To tackle the highly inflectional morphology and to make an open vocabulary translation, we used subwords. Furthermore, the research was conducted on low-data conditions. We used the transformer-based neural machine translation architecture by tuning the hyperparameters for low-data conditions. In the automatic evaluation of the strong baseline, word-based, and subword-based models trained on a public benchmark dataset, the best subword-based models outperform the baseline models by approximately six up to seven BLEU.

Paper Citation

in Harvard Style

Gezmu A., Nürnberger A. and Bati T. (2021). Neural Machine Translation for Amharic-English Translation.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI, ISBN 978-989-758-484-8, pages 526-532. DOI: 10.5220/0010383905260532

in Bibtex Style

@conference{nlpinai21,
author={Andargachew Gezmu and Andreas Nürnberger and Tesfaye Bati},
title={Neural Machine Translation for Amharic-English Translation},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI,},
year={2021},
pages={526-532},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010383905260532},
isbn={978-989-758-484-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI,
TI - Neural Machine Translation for Amharic-English Translation
SN - 978-989-758-484-8
AU - Gezmu A.
AU - Nürnberger A.
AU - Bati T.
PY - 2021
SP - 526
EP - 532
DO - 10.5220/0010383905260532