The challenge of entity matching is that of identifying when different data items (often referred to as records or mentions) refer to the same real-life entity. Popular instantiations of this problem include deduplication, where the items are database records that include duplicate representations of the same entity (e.g., duplicate profiles in a social network) [2], record linkage, where the items come from different data sources that mention overlapping sets of entities (e.g., the profiles of two social networks) [5], and schema matching, where the items are attributes of different database schemas that intersect on their domain of interest (e.g., the database schemas of different social networks) [6].

中文翻译：

---

技术视角

实体匹配的挑战在于识别不同数据项（通常称为记录或提及）何时引用同一现实生活中的实体。此问题的流行实例包括重复数据删除，其中项目是数据库记录，其中包括同一实体的重复表示（例如，社交网络中的重复配置文件）[2]，记录链接，其中项目来自提到重叠的不同数据源实体集（例如，两个社交网络的配置文件）[5]，以及模式匹配，其中项目是不同数据库模式的属性，它们在其感兴趣的领域相交（例如，不同社交网络的数据库模式）[6 ]。