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.
Cite
CITATION STYLE
APA
Navarro, Á., Domingo, M., & Casacuberta, F. (2023). PRHLT’s Submission to WLAC 2023. In Conference on Machine Translation - Proceedings (pp. 875–879). Association for Computational Linguistics. https://doi.org/10.18653/v1/2023.wmt-1.78
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
Already have an account? Sign in
Sign up for free