Abstract
We describe our neural machine translation systems for the WMT22 shared task on unsupervised MT and very low resource supervised MT. We submit supervised NMT systems for Lower Sorbian-German and Lower Sorbian-Upper Sorbian translation in both directions. By using a novel tokenization algorithm, data augmentation techniques, such as Data Diversification (DD), and parameter optimization we improve on our baselines by 10.5-10.77 BLEU for Lower Sorbian-German and by 1.52-1.88 BLEU for Lower Sorbian-Upper Sorbian.- Anthology ID:
- 2022.wmt-1.109
- Volume:
- Proceedings of the Seventh Conference on Machine Translation (WMT)
- Month:
- December
- Year:
- 2022
- Address:
- Abu Dhabi, United Arab Emirates (Hybrid)
- Venue:
- WMT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1111–1116
- Language:
- URL:
- https://aclanthology.org/2022.wmt-1.109
- DOI:
- Cite (ACL):
- Edoardo Signoroni and Pavel Rychlý. 2022. MUNI-NLP Systems for Lower Sorbian-German and Lower Sorbian-Upper Sorbian Machine Translation @ WMT22. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 1111–1116, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- MUNI-NLP Systems for Lower Sorbian-German and Lower Sorbian-Upper Sorbian Machine Translation @ WMT22 (Signoroni & Rychlý, WMT 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.wmt-1.109.pdf