发表机构
The University of Tokyo（东京大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出PragAlign模型，将上下文阅读与选择性澄清分离，经中日母语者评估，该模型在中文场景排名显著优于基线，日语场景最高排名率最高，明确了跨语言判断模式，为回复辅助提供支撑。
AI 中文摘要
多语言场景下的回复辅助需要语言能力与文化情境下的适宜性判断。我们提出PragAlign，该模型将上下文阅读与选择性澄清相分离，并与Direct和Rule两种基线方法一同进行评估。9名汉语母语者对中文材料进行判断，3名日语母语者对匹配的日语版本材料进行判断。在中文评估中，PragAlign的排名显著优于两种基线方法；在日语评估中，Direct的平均排名最低，PragAlign的最高排名率最高，整体差异无统计学意义。两组在10种场景中有5种选择了相同的最优条件，其中包括4次共同选择PragAlign的情况。该研究结果明确了共通及语言特有的判断模式，为旨在支持语言与文化理解的回复辅助工具提供了依据。
英文摘要
Reply assistance in multilingual settings requires linguistic competence and culturally situated judgments of appropriateness. We present PragAlign, which separates context reading from selective clarification, and evaluate it alongside Direct and Rule. Nine native Chinese speakers judged Chinese materials, while three native Japanese speakers judged matched Japanese versions. In the Chinese evaluation, PragAlign received significantly better ranks than both baselines. In the Japanese evaluation, Direct had the lowest mean rank, PragAlign had the highest top-rank rate, and the omnibus difference was not significant. The groups selected the same top condition in 5 of 10 scenarios, including four shared PragAlign selections. The results identify shared and language-specific judgment patterns and inform reply assistance designed to support linguistic and cultural understanding.
Comments5 pages, 5 figures, 2 tables
