ACERPI-Block: Applying Blocking Techniques to the ACERPI Approach

Abstract

Ordinances are documents issued by federal institutions that contain, among others, information regarding their staff. These documents are accessible through public repositories that usually do not allow any filter or advanced search on documents’ contents. This paper extends ACERPI (an approach to collect documents, extract information and resolve entities from institutional ordinances), which identifies the people mentioned in ordinances from institutions to help users find the documents of interest. ACERPI-Block focuses on the Entity Resolution step of the approach, developing blocking strategies that allow scalability to hundreds of thousands of records being resolved. Experiments show a reduction of 93.3% in the number of comparisons of similarity between records if compared to the solution without blocking, with no decrease in efficacy.