Abstract
CycleGN is a Neural Machine Translation framework relying on the Transformer architecture. The foundational concept of our research posits that in an ideal scenario, retro-translations of generated translations should revert to the original source sentences. Consequently, a pair of models can be trained using a Cycle Consistency Loss only, with one model translating in one direction and the second model in the opposite direction.- Anthology ID:
- 2024.wmt-1.66
- Volume:
- Proceedings of the Ninth Conference on Machine Translation
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
- Venue:
- WMT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 756–761
- Language:
- URL:
- https://preview.aclanthology.org/add_missing_videos/2024.wmt-1.66/
- DOI:
- 10.18653/v1/2024.wmt-1.66
- Cite (ACL):
- Sören Dreano, Derek Molloy, and Noel Murphy. 2024. Exploration of the CycleGN Framework for Low-Resource Languages. In Proceedings of the Ninth Conference on Machine Translation, pages 756–761, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- Exploration of the CycleGN Framework for Low-Resource Languages (Dreano et al., WMT 2024)
- PDF:
- https://preview.aclanthology.org/add_missing_videos/2024.wmt-1.66.pdf