Abstract
We present our development of the multilingual machine translation system for the large-scale multilingual machine translation task at WMT 2021. Starting form the provided baseline system, we investigated several techniques to improve the translation quality on the target subset of languages. We were able to significantly improve the translation quality by adapting the system towards the target subset of languages and by generating synthetic data using the initial model. Techniques successfully applied in zero-shot multilingual machine translation (e.g. similarity regularizer) only had a minor effect on the final translation performance.- Anthology ID:
- 2021.wmt-1.51
- 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:
- 425–430
- Language:
- URL:
- https://aclanthology.org/2021.wmt-1.51
- DOI:
- Cite (ACL):
- Danni Liu and Jan Niehues. 2021. Maastricht University’s Large-Scale Multilingual Machine Translation System for WMT 2021. In Proceedings of the Sixth Conference on Machine Translation, pages 425–430, Online. Association for Computational Linguistics.
- Cite (Informal):
- Maastricht University’s Large-Scale Multilingual Machine Translation System for WMT 2021 (Liu & Niehues, WMT 2021)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2021.wmt-1.51.pdf
- Data
- FLORES-101