Abstract
This paper presents the contributions of Charles University teams to the WMT23 General translation task (English to Czech and Czech to Ukrainian translation directions). Our main submission, CUNI-GA, is a result of applying a novel n-best list reranking and modification method on translation candidates produced by the two other submitted systems, CUNI-Transformer and CUNI-DocTransformer (document-level translation only used for the en → cs direction). Our method uses a genetic algorithm and MBR decoding to search for optimal translation under a given metric (in our case, a weighted combination of ChrF, BLEU, COMET22-DA, and COMET22-QE-DA). Our submissions are first in the constrained track and show competitive performance against top-tier unconstrained systems across various automatic metrics.- Anthology ID:
- 2023.wmt-1.8
- Volume:
- Proceedings of the Eighth Conference on Machine Translation
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Philipp Koehn, Barry Haddow, Tom Kocmi, Christof Monz
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 119–127
- Language:
- URL:
- https://aclanthology.org/2023.wmt-1.8
- DOI:
- 10.18653/v1/2023.wmt-1.8
- Cite (ACL):
- Josef Jon, Martin Popel, and Ondřej Bojar. 2023. CUNI at WMT23 General Translation Task: MT and a Genetic Algorithm. In Proceedings of the Eighth Conference on Machine Translation, pages 119–127, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- CUNI at WMT23 General Translation Task: MT and a Genetic Algorithm (Jon et al., WMT 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/2023.wmt-1.8.pdf