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)
- Editors:
- Philipp Koehn, Loïc Barrault, Ondřej Bojar, Fethi Bougares, Rajen Chatterjee, Marta R. Costa-jussà, Christian Federmann, Mark Fishel, Alexander Fraser, Markus Freitag, Yvette Graham, Roman Grundkiewicz, Paco Guzman, Barry Haddow, Matthias Huck, Antonio Jimeno Yepes, Tom Kocmi, André Martins, Makoto Morishita, Christof Monz, Masaaki Nagata, Toshiaki Nakazawa, Matteo Negri, Aurélie Névéol, Mariana Neves, Martin Popel, Marco Turchi, Marcos Zampieri
- Venue:
- WMT
- SIG:
- SIGMT
- 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/cschoel_rss_and_blog/2022.wmt-1.109.pdf