Abstract

Querying a relational database is difficult because it requires the user to have a grasp of the relational model, the SQL language, and the schema at hand. While natural language interfaces (NLIs) and programming-by-example (PBE) are promising alternatives, they suffer from various challenges. Natural language queries (NLQs) are often ambiguous, even for human interpreters, and current PBE approaches require either low-complexity queries, user schema knowledge, exact example tuples from the user, or a closed-world assumption to be tractable. Consequently, we propose dual-specification query synthesis which consumes both a NLQ and an optional PBElike table sketch query that enables users to express varied levels of knowledge. We introduce the Duoqest system, which leverages guided partial query enumeration to efficiently explore the space of possible queries. We demonstrate in experiments on the prominent Spider benchmark that Duoqest substantially outperforms state-of-the-art NLI and PBE approaches.