跳到正文
研踪PaperTrail
← 研踪 PaperTrail

ACL Anthology · ACL 2026:acl:2026.acl-industry.63 · 记录 #1

Multi-Agent Orchestration for Terminology-Constrained Machine Translation in Industrial Localization

来源日期(仅到月份) 2026-07
来源记录日期 2026-07
雷达观测 2026-11-01 22:08
ACL Anthology · ACL 2026 ↗PDF ↗

摘要

Accurate terminology is a non-negotiable requirement in industrial localization processes: a single mistranslated domain term can violate contractual obligations and erode client trust.We present AIDA\textsubscript{term}, a deployed multi-agent LLM pipeline that orchestrates four specialized agents—Analysis, Translation, Post-editing, and Review—for terminology-constrained machine translation.The system introduces terminology-aware pre-analysis, explicit glossary injection at every pipeline stage, and a reasoning-enabled Review agent.We evaluate six configurations on the WMT25 Terminology Translation benchmark (Track 1: en\tode/es/ru, IT domain), enabling systematic ablation of each design choice.Our best configuration achieves 99.4% average terminology accuracy while attaining the highest ChrF2++ scores across all three language pairs, outperforming all 20 systems submitted to the shared task.Unlike other multi-agent approaches in WMT25 that rely on generate-and-select strategies, AIDA\textsubscript{term} is the first to apply a role-specialized sequential pipeline to terminology-constrained MT, and is deployed with native XLIFF integration for seamless CAT tool interoperability.The system processes thousands of terminology-constrained requests daily at a large localization provider.

论文发现出处

这些页面提供论文线索,不代表同行评审或质量认证。

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

发表信息与关联版本

版本差异

目前只观测到一个版本,无法比较变化。之后收录新版本时,会在这里对照标题、作者、分类和摘要。

观测到的版本

平台记录号代表本站观测到的元数据变化,不是作者修订号。来源日期仅到月份或年份时,按该月或该年首日存档。

记录 #1 · 2026-07 · 最新观测版本

Multi-Agent Orchestration for Terminology-Constrained Machine Translation in Industrial Localization

Accurate terminology is a non-negotiable requirement in industrial localization processes: a single mistranslated domain term can violate contractual obligations and erode client trust.We present AIDA\textsubscript{term}, a deployed multi-agent LLM pipeline that orchestrates four specialized agents—Analysis, Translation, Post-editing, and Review—for terminology-constrained machine translation.The system introduces terminology-aware pre-analysis, explicit glossary injection at every pipeline stage, and a reasoning-enabled Review agent.We evaluate six configurations on the WMT25 Terminology Translation benchmark (Track 1: en\tode/es/ru, IT domain), enabling systematic ablation of each design choice.Our best configuration achieves 99.4% average terminology accuracy while attaining the highest ChrF2++ scores across all three language pairs, outperforming all 20 systems submitted to the shared task.Unlike other multi-agent approaches in WMT25 that rely on generate-and-select strategies, AIDA\textsubscript{term} is the first to apply a role-specialized sequential pipeline to terminology-constrained MT, and is deployed with native XLIFF integration for seamless CAT tool interoperability.The system processes thousands of terminology-constrained requests daily at a large localization provider.

查看此版本解读 →查看此版本原文 ↗