Abstract
This paper describes our submission to the Word-Level AutoCompletion shared task of WMT23. We participated in the English–German and German–English categories. We extended our last year segment-based interactive machine translation approach to address its weakness when no context is available. Additionally, we fine-tune the pre-trained mT5 large language model to be used for autocompletion.- Anthology ID:
- 2023.wmt-1.78
- 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:
- 877–881
- Language:
- URL:
- https://aclanthology.org/2023.wmt-1.78
- DOI:
- 10.18653/v1/2023.wmt-1.78
- Cite (ACL):
- Angel Navarro, Miguel Domingo, and Francisco Casacuberta. 2023. PRHLT’s Submission to WLAC 2023. In Proceedings of the Eighth Conference on Machine Translation, pages 877–881, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- PRHLT’s Submission to WLAC 2023 (Navarro et al., WMT 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2023.wmt-1.78.pdf