Nominations for Chair of the TC on Data Engineering

An important aspect of maintaining information quality in data repositories is determining which sets of records refer to the same real world entity. This so called entity resolution problem comes up frequently for data cleaning and integration. In many domains, the underlying entities exhibit strong ties between themselves. Friendships in social networks and collaborations between researchers are examples of such ties. In such cases, we stress the need for collective entity resolution where, instead of independently tagging pairs of records as duplicates or non-duplicates, related entities are resolved collectively. We present different algorithms for collective entity resolution that combine relational evidence with traditional attribute-based approaches to improve entity resolution performance in a scalable manner.