Context-aware and Style-related Incremental Decoding Framework for Discourse-Level Literary Translation

Yuanchang Luo, Jiaxin Guo, Daimeng Wei, Hengchao Shang, Zongyao Li, Zhanglin Wu, Zhiqiang Rao, Shaojun Li, Jinlong Yang, Hao Yang


Abstract
This report outlines our approach for the WMT24 Discourse-Level Literary Translation Task, focusing on the Chinese-English language pair in the Constrained Track. Translating literary texts poses significant challenges due to the nuanced meanings, idiomatic expressions, and intricate narrative structures inherent in such works. To address these challenges, we leveraged the Chinese-Llama2 model, specifically enhanced for this task through a combination of Continual Pre-training (CPT) and Supervised Fine-Tuning (SFT). Our methodology includes a novel Incremental Decoding framework, which ensures that each sentence is translated with consideration of its broader context, maintaining coherence and consistency throughout the text. This approach allows the model to capture long-range dependencies and stylistic elements, producing translations that faithfully preserve the original literary quality. Our experiments demonstrate significant improvements in both sentence-level and document-level BLEU scores, underscoring the effectiveness of our proposed framework in addressing the complexities of document-level literary translation.
Anthology ID:
2024.wmt-1.97
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:
973–979
Language:
URL:
https://aclanthology.org/2024.wmt-1.97
DOI:
Bibkey:
Cite (ACL):
Yuanchang Luo, Jiaxin Guo, Daimeng Wei, Hengchao Shang, Zongyao Li, Zhanglin Wu, Zhiqiang Rao, Shaojun Li, Jinlong Yang, and Hao Yang. 2024. Context-aware and Style-related Incremental Decoding Framework for Discourse-Level Literary Translation. In Proceedings of the Ninth Conference on Machine Translation, pages 973–979, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Context-aware and Style-related Incremental Decoding Framework for Discourse-Level Literary Translation (Luo et al., WMT 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.wmt-1.97.pdf