Multilingual Transfer and Domain Adaptation for Low-Resource Languages of Spain
Yuanchang Luo, Zhanglin Wu, Daimeng Wei, Hengchao Shang, Zongyao Li, Jiaxin Guo, Zhiqiang Rao, Shaojun Li, Jinlong Yang, Yuhao Xie, Zheng Jiawei, Bin Wei, Hao Yang
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 (es2arg), spanish to aranese (es2arn), and spanish to asturian (es2ast). 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.- Anthology ID:
- 2024.wmt-1.93
- Volume:
- Proceedings of the Ninth Conference on Machine Translation
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
- Venue:
- WMT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 949–954
- Language:
- URL:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2024.wmt-1.93/
- DOI:
- 10.18653/v1/2024.wmt-1.93
- Cite (ACL):
- Yuanchang Luo, Zhanglin Wu, Daimeng Wei, Hengchao Shang, Zongyao Li, Jiaxin Guo, Zhiqiang Rao, Shaojun Li, Jinlong Yang, Yuhao Xie, Zheng Jiawei, Bin Wei, and Hao Yang. 2024. Multilingual Transfer and Domain Adaptation for Low-Resource Languages of Spain. In Proceedings of the Ninth Conference on Machine Translation, pages 949–954, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- Multilingual Transfer and Domain Adaptation for Low-Resource Languages of Spain (Luo et al., WMT 2024)
- PDF:
- https://preview.aclanthology.org/build-pipeline-with-new-library/2024.wmt-1.93.pdf