Multilingual Transfer and Domain Adaptation for Low-Resource Languages of Spain
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912049533026304 |
|---|---|
| author | Luo, Yuanchang Wu, Zhanglin Wei, Daimeng Shang, Hengchao Li, Zongyao Guo, Jiaxin Rao, Zhiqiang Li, Shaojun Yang, Jinlong Xie, Yuhao Wei, Jiawei Zheng Bin Yang, Hao |
| author_facet | Luo, Yuanchang Wu, Zhanglin Wei, Daimeng Shang, Hengchao Li, Zongyao Guo, Jiaxin Rao, Zhiqiang Li, Shaojun Yang, Jinlong Xie, Yuhao Wei, Jiawei Zheng Bin Yang, Hao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_15924 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multilingual Transfer and Domain Adaptation for Low-Resource Languages of Spain Luo, Yuanchang Wu, Zhanglin Wei, Daimeng Shang, Hengchao Li, Zongyao Guo, Jiaxin Rao, Zhiqiang Li, Shaojun Yang, Jinlong Xie, Yuhao Wei, Jiawei Zheng Bin Yang, Hao Computation and Language Artificial Intelligence 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. |
| title | Multilingual Transfer and Domain Adaptation for Low-Resource Languages of Spain |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2409.15924 |