DivEMT：跨不同类型学语言的神经机器翻译后编辑工作量研究
DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages
AI总结：
本文介绍了DivEMT，首个涵盖多种类型学目标语言的神经机器翻译后编辑公开研究，通过18名专业译者的行为数据评估了Google Translate和mBART-50系统对翻译生产力的影响，发现后编辑虽普遍快于从零翻译，但增益幅度因语言类型学差异而显著不同。
摘要：
我们介绍了DivEMT，这是首个公开可用的神经机器翻译（NMT）后编辑研究，涵盖了一组类型学上不同的目标语言。在严格控制的设置下，18名专业翻译人员被指示将同一组英文文档翻译或后编辑为阿拉伯语、荷兰语、意大利语、土耳其语、乌克兰语和越南语。在此过程中，记录了他们的编辑、按键、编辑时间和停顿，从而能够对NMT质量和后编辑有效性进行深入的跨语言评估。利用这个新数据集，我们评估了两种最先进的NMT系统，即Google Translate和多语言mBART-50模型，对翻译生产力的影响。我们发现后编辑始终比从头翻译更快。然而，生产力提升的幅度在系统和语言之间差异很大，突显了在与英语类型学相关程度不同的语言在后编辑有效性上的重大差异，即使在控制系统架构和训练数据规模时也是如此。我们公开发布包括所有收集的行为数据在内的完整数据集，以促进对NMT系统在类型学多样语言翻译能力上的新研究。
英文摘要：
We introduce DivEMT, the first publicly available post-editing study of Neural Machine Translation (NMT) over a typologically diverse set of target languages. Using a strictly controlled setup, 18 professional translators were instructed to translate or post-edit the same set of English documents into Arabic, Dutch, Italian, Turkish, Ukrainian, and Vietnamese. During the process, their edits, keystrokes, editing times and pauses were recorded, enabling an in-depth, cross-lingual evaluation of NMT quality and post-editing effectiveness. Using this new dataset, we assess the impact of two state-of-the-art NMT systems, Google Translate and the multilingual mBART-50 model, on translation productivity. We find that post-editing is consistently faster than translation from scratch. However, the magnitude of productivity gains varies widely across systems and languages, highlighting major disparities in post-editing effectiveness for languages at different degrees of typological relatedness to English, even when controlling for system architecture and training data size. We publicly release the complete dataset including all collected behavioral data, to foster new research on the translation capabilities of NMT systems for typologically diverse languages.
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。
