The Call for Recall

General-purpose knowledge bases (KBs) such as YAGO, Wikidata or the Google Knowledge Graph usually contain facts that have a high precision. In contrast, little is known about the recall of such KBs, and anecdotal evidence indicates that knowledge bases have a low recall on many topics. This project aims to develop techniques to evaluate and improve the recall of knowledge bases. We aim to use focus on text extraction in this approach, and to compare the result with a complementary approach using rule mining. In cooperation with the Wikimedia Foundation, the output from both techniques shall lead to an extension for Wikidata which uses the retrieved recall information in order to help users in viewing, adding and managing recall information.