CHORUS: Effort-Aware Multi-Agent Human-AI Collaboration for Professional Translation

TL;DR

CHORUS is a multi-agent AI translation system that supports professional translators by reducing time, effort, and improving quality through personalized, mixed-initiative collaboration.

Contribution

This work introduces CHORUS, a novel mixed-initiative translation system that adapts to individual translator traits and enhances professional translation workflows.

Findings

Reduced translation completion time by 33.8%

Lowered cognitive effort for translators

Improved translation quality as measured by BLEU and COMET

Abstract

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.