基于LLM的文学翻译中的情感特征:机器翻译与译后编辑的系统性转变
Emotion Profiling in LLM-Based Literary Translation: Systematic Shifts Across MT and Post-Editing
AI总结:
研究LLM翻译的情感特征及译后编辑如何使其接近人类翻译,通过对比《Oryx and Crake》的LLM翻译、译后编辑版本和人类翻译,发现MT系统引入特定情感指纹,削弱作者声音。
摘要:
本文研究LLM翻译是否表现出可识别的情感特征,以及译后编辑如何将其重塑为更接近人类的标准。我们比较了玛格丽特·阿特伍德《Oryx and Crake》的LLM翻译及其译后编辑版本和人类翻译,以当代意大利科幻小说的大规模语料库为基线。通过基于词典和多语言建模的方法,我们对不同系统的情感变化进行了细粒度分析。我们发现,机器翻译系统在翻译中引入了特定模型且统计显著的情感指纹,导致作者声音的保留有限。
英文摘要:
This paper investigates whether LLM translations exhibit identifiable emotional profiles and how post-editing reshapes them toward human-like norms. We compare LLM translations of Margaret Atwood's Oryx and Crake with their post-edited versions and a human translation, using a large-scale corpus of contemporary Italian science-fiction as a baseline. We examine emotion through lexicon-based and multilingual modeling, conducting a fine-grained analysis of emotional variation across systems. We find that MT systems introduce model-specific and statistically significant emotional fingerprints across translations, leading to a limited preservation of an author's voice.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。