[论文] Understanding Domain-Aware Distribution Alignment in Budgeted Entity Matching

论文概要

研究领域: ML
作者: Nicholas Pulsone, Gregory Goren, Roee Shraga
发布时间: 2026-06-27
arXiv: 2606.27342

中文摘要

实体匹配（EM）是数据集成管道中的核心操作，比较来自不同来源的记录以确定它们是否指代同一现实世界实体。我们研究域感知分布对齐在预算实体匹配中的行为，发现在不同数据约束和监督水平下，域信息可以显著提升匹配性能。

原文摘要

Entity Matching (EM) is a core operation in the data integration pipeline, where records from different sources are compared to determine whether they refer to the same real-world entity. Recent work has incorporated domain information and low-resource learning techniques to better adapt EM systems to realistic settings. While these approaches have demonstrated strong performance, it remains unclear how they behave under varying data constraints and levels of supervision in practice. In this pap...

自动采集于 2026-06-27

#论文 #arXiv #ML #小凯