arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.19016cs.HC
收藏

CHORUS:面向专业翻译的有意识多智能体人机协作

CHORUS: Designing Human-AI Multi-Agent Collaboration for Professional Translators

New York University(纽约大学);Stony Brook University(石溪大学);Middlebury Institute of International Studies at Monterey(蒙特雷国际研究学院);Tandon School of Engineering, New York University(纽约大学坦登工程学院);College of Electronic and Information Engineering , Tongji University(同济大学电子与信息工程学院)

George Xi Wang, Jiaqian Hu, Guande Wu, Jing Qian

AI总结:

CHORUS通过多智能体协作系统支持翻译流程与个人风格,减少译者认知负担,提升翻译质量,降低完成时间33.8%。

摘要:

尽管自动AI翻译系统在日常语言任务中广泛应用,专业翻译在领域特定和高风险场景中仍至关重要。然而,专业译员很少依赖这些系统,因为缺乏对翻译过程的详细支持、匹配专业风格以及对最终结果的责任。为此,我们提出了CHORUS,一种混合发起的翻译系统,支持译者在工作中的翻译流程和个人风格。一项形成性研究发现,结合MQM理论可能有助于实现专业翻译,并且系统应适应每位译者的独特特征。最终的30名英语-中文专业译员的内组研究发现,我们的系统将完成时间减少了33.8%,降低了译者的认知努力,并通过BLEU和COMET等自动评估指标提高了最终翻译质量。参与者定性分析还显示,该系统使翻译问题更容易检查,减少了与单智能体AI系统相比的重复提示,并提供了对译者习惯和特征的反思。我们的发现展示了多智能体AI系统如何设计以支持专家工作流程及其在专业应用中的潜力。

英文摘要:

Despite the widespread use of automatic AI translation systems in daily language tasks, professional translation remains crucial in domain-specific and high-stakes scenarios. Yet professional translators rarely rely on these systems in their everyday practice due to a lack of detailed support for the translation process, matching professional styles, and accountability for the final outcome. To bridge the gap, we present CHORUS, a mixed-initiative translation system that supports the translation process and personal style as translators work. A formative study found that incorporating MQM theory may be beneficial for achieving professional translation, and that the system should adapt to each individual translator's idiosyncratic traits. The final within-subject study with 30 licensed English--Chinese translators found that our system reduced completion time by 33.8\%, lowered translators' cognitive effort, and improved final translation quality using the BLEU and COMET as automatic evaluation metrics. Participants' qualitative analysis also revealed that the system made translation issues easier to inspect, reduced repeated prompting compared to single-agent AI systems, and offered reflections on their habits and traits. Our findings illustrate how multi-agent AI systems can be designed to support expert workflows and their potential for professional use.

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。

↑