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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Luo, Yuanchang, Guo, Jiaxin, Wei, Daimeng, Shang, Hengchao, Li, Zongyao, Wu, Zhanglin, Rao, Zhiqiang, Li, Shaojun, Yang, Jinlong, Yang, Hao
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929519349202944
author Luo, Yuanchang
Guo, Jiaxin
Wei, Daimeng
Shang, Hengchao
Li, Zongyao
Wu, Zhanglin
Rao, Zhiqiang
Li, Shaojun
Yang, Jinlong
Yang, Hao
author_facet Luo, Yuanchang
Guo, Jiaxin
Wei, Daimeng
Shang, Hengchao
Li, Zongyao
Wu, Zhanglin
Rao, Zhiqiang
Li, Shaojun
Yang, Jinlong
Yang, Hao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_16539
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Context-aware and Style-related Incremental Decoding framework for Discourse-Level Literary Translation
Luo, Yuanchang
Guo, Jiaxin
Wei, Daimeng
Shang, Hengchao
Li, Zongyao
Wu, Zhanglin
Rao, Zhiqiang
Li, Shaojun
Yang, Jinlong
Yang, Hao
Artificial Intelligence
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.
title Context-aware and Style-related Incremental Decoding framework for Discourse-Level Literary Translation
topic Artificial Intelligence
url https://arxiv.org/abs/2409.16539