Multilingual Transfer and Domain Adaptation for Low-Resource Languages of Spain
Abstract
This article introduces the submission status of the Translation into Low-Resource Languages of Spain task at (WMT 2024) by Huawei Translation Service Center (HW-TSC). We participated in three translation tasks: spanish to aragonese (es-arg), spanish to aranese (es-arn), and spanish to asturian (es-ast). For these three translation tasks, we use training strategies such as multilingual transfer, regularized dropout, forward translation and back translation, labse denoising, transduction ensemble learning and other strategies to neural machine translation (NMT) model based on training deep transformer-big architecture. By using these enhancement strategies, our submission achieved a competitive result in the final evaluation.
Keywords
Cite
@article{arxiv.2409.15924,
title = {Multilingual Transfer and Domain Adaptation for Low-Resource Languages of Spain},
author = {Yuanchang Luo and Zhanglin Wu and Daimeng Wei and Hengchao Shang and Zongyao Li and Jiaxin Guo and Zhiqiang Rao and Shaojun Li and Jinlong Yang and Yuhao Xie and Jiawei Zheng Bin Wei and Hao Yang},
journal= {arXiv preprint arXiv:2409.15924},
year = {2024}
}
Comments
6 pages,wmt24. arXiv admin note: substantial text overlap with arXiv:2409.14842; text overlap with arXiv:2409.14800