更智能的编辑?基于错误高亮和翻译建议的后编辑
Smarter edits? Post-editing with error highlights and translation suggestions
AI总结:
本文研究了基于自动后编辑(APE)的错误高亮和纠正建议在后编辑任务中的有效性,发现虽然没有提升生产力和质量,但APE高亮和纠正建议提升了用户体验。
摘要:
随着机器翻译质量的提高,对增强的后编辑功能(如基于QE的错误高亮)的兴趣正在增长,但其有用性的证据仍然有限。在本文中,我们探讨了基于自动后编辑(APE)的错误高亮和纠正建议的有用性。我们进行了一项研究,让专业翻译员(En-Nl)使用APE错误高亮和纠正建议进行后编辑,并将生产力、质量和用户体验与常规PE和带有QE衍生高亮的PE进行比较。尽管没有条件相比常规PE在生产力或质量上有所提升,但APE高亮比QE衍生高亮更受好评,而纠正建议提高了整体的用户体验。
英文摘要:
As MT quality increases, interest in enhanced post-editing features such as QE-derived error highlights is growing, yet evidence for their usefulness remains limited. In this work, we explore the usefulness of LLM-derived error highlights and correction suggestions based on automatic post-editing (APE). We conduct a study where professional translators (En-Nl) post-edit translations using APE error highlights and correction suggestions and compare productivity, quality and user experience to regular PE and PE with QE-derived highlights. While no condition yielded productivity or quality gains compared to regular PE, APE highlights were better received than QE-derived highlights, and correction suggestions improved overall user experience.
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。