NovelTrans: System for WMT24 Discourse-Level Literary Translation

Yuchen Liu, Yutong Yao, Runzhe Zhan, Yuchu Lin, Derek F. Wong


Abstract
This paper describes our submission system, NovelTrans, from NLP²CT and DeepTranx for the WMT24 Discourse-Level Literary Translation Task in Chinese-English, Chinese-German, and Chinese-Russian language pairs under unconstrained conditions. For our primary system, three translations are done by GPT4o using three different settings of additional information and a terminology table generated by online models. The final result is composed of sentences that have the highest xCOMET score compared with the corresponding sentences in other results. Our system achieved an xCOMET score of 79.14 which is higher than performing a direct chapter-level translation on our dataset.
Anthology ID:
2024.wmt-1.98
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:
980–986
Language:
URL:
https://aclanthology.org/2024.wmt-1.98
DOI:
Bibkey:
Cite (ACL):
Yuchen Liu, Yutong Yao, Runzhe Zhan, Yuchu Lin, and Derek F. Wong. 2024. NovelTrans: System for WMT24 Discourse-Level Literary Translation. In Proceedings of the Ninth Conference on Machine Translation, pages 980–986, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
NovelTrans: System for WMT24 Discourse-Level Literary Translation (Liu et al., WMT 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.wmt-1.98.pdf