Strengthening Low-resource Neural Machine Translation through Joint Learning: The Case of Farsi-Spanish

Benyamin Ahmadnia, Raul Aranovich, Bonnie Dorr

2021

Abstract

This paper describes a systematic study of an approach to Farsi-Spanish low-resource Neural Machine Translation (NMT) that leverages monolingual data for joint learning of forward and backward translation models. As is standard for NMT systems, the training process begins using two pre-trained translation models that are iteratively updated by decreasing translation costs. In each iteration, either translation model is used to translate monolingual texts from one language to another, to generate synthetic datasets for the other translation model. Two new translation models are then learned from bilingual data along with the synthetic texts. The key distinguishing feature between our approach and standard NMT is an iterative learning process that improves the performance of both translation models, simultaneously producing a higher-quality synthetic training dataset upon each iteration. Our empirical results demonstrate that this approach outperforms baselines.

Paper Citation

in Harvard Style

Ahmadnia B., Aranovich R. and Dorr B. (2021). Strengthening Low-resource Neural Machine Translation through Joint Learning: The Case of Farsi-Spanish.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI, ISBN 978-989-758-484-8, pages 475-481. DOI: 10.5220/0010362604750481

in Bibtex Style

@conference{nlpinai21,
author={Benyamin Ahmadnia and Raul Aranovich and Bonnie Dorr},
title={Strengthening Low-resource Neural Machine Translation through Joint Learning: The Case of Farsi-Spanish},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 1: NLPinAI,},
year={2021},
pages={475-481},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010362604750481},
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 - Strengthening Low-resource Neural Machine Translation through Joint Learning: The Case of Farsi-Spanish
SN - 978-989-758-484-8
AU - Ahmadnia B.
AU - Aranovich R.
AU - Dorr B.
PY - 2021
SP - 475
EP - 481
DO - 10.5220/0010362604750481