Abstract
Multilingual Neural Machine Translation (MNMT) enables one system to translate sentences from multiple source languages to multiple target languages, greatly reducing deployment costs compared with conventional bilingual systems. The MNMT training benefit, however, is often limited to many-to-one directions. The model suffers from poor performance in one-to-many and many-to-many with zero-shot setup. To address this issue, this paper discusses how to practically build MNMT systems that serve arbitrary X-Y translation directions while leveraging multilinguality with a two-stage training strategy of pretraining and finetuning. Experimenting with the WMT’21 multilingual translation task, we demonstrate that our systems outperform the conventional baselines of direct bilingual models and pivot translation models for most directions, averagely giving +6.0 and +4.1 BLEU, without the need for architecture change or extra data collection. Moreover, we also examine our proposed approach in an extremely large-scale data setting to accommodate practical deployment scenarios.- Anthology ID:
- 2022.naacl-main.44
- Volume:
- Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 600–606
- Language:
- URL:
- https://aclanthology.org/2022.naacl-main.44
- DOI:
- 10.18653/v1/2022.naacl-main.44
- Cite (ACL):
- Akiko Eriguchi, Shufang Xie, Tao Qin, and Hany Hassan. 2022. Building Multilingual Machine Translation Systems That Serve Arbitrary XY Translations. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 600–606, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- Building Multilingual Machine Translation Systems That Serve Arbitrary XY Translations (Eriguchi et al., NAACL 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.naacl-main.44.pdf