Augmented Spanish-Persian Neural Machine Translation

Benyamin Ahmadnia, Raul Aranovich

Abstract

Neural Machine Translation (NMT) performs training of a neural network employing an encoder-decoder architecture. However, the quality of the neural-based translations predominantly depends on the availability of a large amount of bilingual training dataset. In this paper, we explore the performance of translations predicted by attention-based NMT systems for Spanish to Persian low-resource language pairs. We analyze the errors of NMT systems that occur in the Persian language and provide an in-depth comparison of the performance of the system based on variations in sentence length and size of the training dataset. We evaluate our translation results using BLEU and human evaluation measures based on the adequacy, fluency, and overall rating.

Download


Paper Citation


in Harvard Style

Ahmadnia B. and Aranovich R. (2021). Augmented Spanish-Persian Neural Machine Translation.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI, ISBN 978-989-758-484-8, pages 482-488. DOI: 10.5220/0010369804820488


in Bibtex Style

@conference{nlpinai21,
author={Benyamin Ahmadnia and Raul Aranovich},
title={Augmented Spanish-Persian Neural Machine Translation},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI,},
year={2021},
pages={482-488},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010369804820488},
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 - Augmented Spanish-Persian Neural Machine Translation
SN - 978-989-758-484-8
AU - Ahmadnia B.
AU - Aranovich R.
PY - 2021
SP - 482
EP - 488
DO - 10.5220/0010369804820488