Abstract
The ARC-NKUA (“Athena” Research Center - National and Kapodistrian University of Athens) submission to the WMT22 General Machine Translation shared task concerns the unconstrained tracks of the English-Ukrainian and Ukrainian-English translation directions. The two Neural Machine Translation systems are based on Transformer models and our primary submissions were determined through experimentation with (a) ensemble decoding, (b) selected fine-tuning with a subset of the training data, (c) data augmentation with back-translated monolingual data, and (d) post-processing of the translation outputs. Furthermore, we discuss filtering techniques and the acquisition of additional data used for training the systems.- Anthology ID:
- 2022.wmt-1.31
- 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:
- 358–365
- Language:
- URL:
- https://aclanthology.org/2022.wmt-1.31
- DOI:
- Cite (ACL):
- Dimitrios Roussis and Vassilis Papavassiliou. 2022. The ARC-NKUA Submission for the English-Ukrainian General Machine Translation Shared Task at WMT22. In Proceedings of the Seventh Conference on Machine Translation (WMT), pages 358–365, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics.
- Cite (Informal):
- The ARC-NKUA Submission for the English-Ukrainian General Machine Translation Shared Task at WMT22 (Roussis & Papavassiliou, WMT 2022)
- PDF:
- https://preview.aclanthology.org/paclic-22-ingestion/2022.wmt-1.31.pdf