Abstract
This paper describes Huawei Artificial Intelligence Application Research Center’s neural machine translation systems and submissions to the WMT21 biomedical translation shared task. Four of the submissions achieve state-of-the-art BLEU scores based on the official-released automatic evaluation results (EN->FR, EN<->IT and ZH->EN). We perform experiments to unveil the practical insights of the involved domain adaptation techniques, including finetuning order, terminology dictionaries, and ensemble decoding. Issues associated with overfitting and under-translation are also discussed.- Anthology ID:
- 2021.wmt-1.88
- Volume:
- Proceedings of the Sixth Conference on Machine Translation
- Month:
- November
- Year:
- 2021
- Address:
- Online
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 868–873
- Language:
- URL:
- https://aclanthology.org/2021.wmt-1.88
- DOI:
- Cite (ACL):
- Weixuan Wang, Wei Peng, Xupeng Meng, and Qun Liu. 2021. Huawei AARC’s Submissions to the WMT21 Biomedical Translation Task: Domain Adaption from a Practical Perspective. In Proceedings of the Sixth Conference on Machine Translation, pages 868–873, Online. Association for Computational Linguistics.
- Cite (Informal):
- Huawei AARC’s Submissions to the WMT21 Biomedical Translation Task: Domain Adaption from a Practical Perspective (Wang et al., WMT 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.wmt-1.88.pdf