DeepTrans Studio: Turning Expert Interventions into Shared Team Knowledge in Agentic Translation Workflows

2026-06-28

AI Summary

This work addresses a critical limitation in current large language model–based translation tools, which treat human post-editing as an isolated action and fail to convert expert decisions into reusable team knowledge. To overcome this, the authors propose a collaborative translation workspace featuring a human–AI intervention mechanism that enables experts to review evidence, revise outputs at key stages of the agent-driven translation pipeline, and store validated decisions in a shared memory. The system uniquely supports traceability and cross-user, cross-document reuse of human interventions. Integrated with terminology management and legal modality risk detection, it demonstrates the ability to automatically propagate expert decisions to downstream segments and surface them as precedents within teammates’ workspaces, thereby enhancing collective translation consistency and efficiency.

Abstract

Professional translation is often a team-based process: translators, reviewers, and project managers must coordinate terminology, legal force, and accountability across documents. Yet many LLM-based translation tools treat human corrections as isolated edits. Expert decisions made in one segment or by one member are rarely captured as reusable knowledge for the rest of the team. We present DeepTrans Studio, a collaborative translation workspace that lets professionals intercept selected nodes in an agentic translation workflow, review evidence, revise AI outputs, and save approved decisions to a shared team memory. During the demo, attendees will role-play translators and reviewers, resolve preset terminology and legal-modal risks, and see how their decisions are propagated to downstream segments and surfaced in a teammate's workspace as reusable precedents. The demo illustrates how human interventions in AI-mediated work can become shared, traceable knowledge rather than one-off corrections.

Problem

• translation workflow
• expert intervention
• shared knowledge
• team collaboration
• LLM-based translation

Innovation

• agentic translation
• shared team memory
• human-AI collaboration
• translation workflow
• reusable knowledge