文学翻译中的人类与机器翻译的流畅性与忠实性
Fluency and Faithfulness in Human and Machine Literary Translation
AI总结：
研究通过分析13万段翻译文本，探讨流畅性与忠实性之间的平衡，发现流畅性与忠实性呈负相关，尤其在机器翻译中表现较弱。
摘要：
文学翻译需要在目标语言的流畅性与源语言的忠实性之间取得平衡。最近的大型语言模型（LLMs）通常产生流畅的翻译，但尚不清楚流畅性是否在文学文本中对应语义保持。我们使用130,486段来自106部小说的翻译段落，包括人类、谷歌翻译和TranslateGemma的翻译，来检验这种关系。流畅性通过训练在段落词性标注n-gram上的翻译ese分类器来测量，忠实性则使用自动翻译评估度量标准COMET-KIWI。我们控制了段落长度，并发现流畅性与忠实性之间存在一致的负相关关系。这种模式在人类和谷歌翻译中出现，但在TranslateGemma中则较弱且通常不显著。这些结果表明，段落长度对自动评估至关重要，并表明在文学翻译中存在流畅性与忠实性之间的权衡。
英文摘要：
Literary translation requires balancing target-language fluency with faithfulness to the source. Recent large language models (LLMs) often produce fluent translations, but it remains unclear whether fluency corresponds to semantic preservation in literary text. We examine this relationship using 130,486 translated paragraphs from 106 novels in 16 source languages, including human, Google Translate, and TranslateGemma translations. Fluency is measured as original-likeness with a translationese classifier trained on paragraph part-of-speech n-grams, and faithfulness with the automatic translation evaluation metric COMET-KIWI. We control for paragraph length and find a consistent negative correlation between fluency and faithfulness. The pattern appears for both human and Google Translate, but is weaker and often non-significant for TranslateGemma. These results show that segment length matters for automatic evaluation and suggest a tradeoff between fluency and faithfulness in literary translation.
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。
