Interactive rule correction, imputation and execution in rule-driven database completion system

摘要

This paper solves the problem of correcting database completion rules, imputing missing rule conditions, and executing them interactively and efficiently. Often in real-world scenarios, database completion rules have syntactic errors. Even after correcting these rules, the process of correction can introduce spurious rule conditions that can result in inefficient rule execution. We solve this problem by leveraging programming-by-example data transformations, sketching data structures such as bloom filters, and leveraging entity resolution rules. The paper proposes to use programming-by-example data transformations along with reducing the size of examples generated for it. We build upon current work to involve the user in the process of making PBE examples. The paper also proposes to use sketching data structures for the database completion process under dynamic rules, along with reducing their numbers and sizes of them. We again build upon existing work to involve the user in the process of making a summary on an incomplete database, which also increases efficiency. The paper also proposes to efficiently leverage entity resolution rules to find missing rule conditions in database completion rules.