一篇新论文探讨了文学译后编辑在使用神经机器翻译（NMT）和大型语言模型（LLMs）翻译隐喻时面临的挑战。研究发现，译后编辑平均每三个隐喻中就会修改一个，这表明在文学语境下，比喻性语言的翻译存在显著问题。参与者认为机器翻译的输出质量很差，译后编辑所需付出的努力比从头开始翻译还要多，这也影响了他们的创作自由和所有权感。 AI
影响 强调了在细致的文学翻译中使用大型语言模型和神经机器翻译所面临的重大挑战，表明当前模型可能阻碍而非促进创造性的译后编辑。
排序理由 该集群包含一篇讨论神经机器翻译和大型语言模型在特定语言任务上表现的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
This paper investigates how post-editors of literary texts react and respond to the way metaphors have been translated by Neu ral Machine Translation (NMT) and Large Language Models (LLMs). The results show that one in three metaphors in the output were changed by the post-editor…
This paper investigates how post-editors of literary texts react and respond to the way metaphors have been translated by Neu ral Machine Translation (NMT) and Large Language Models (LLMs). The results show that one in three metaphors in the output were changed by the post-editor…