Learning to generate structured queries from natural language with indirect supervision

•We design an end-to-end neural model based on COPYNET with policy-based reinforcement learning within the answer-driven learning paradigm.•Experimental results show that our model outperforms the baseline models.•We elaborately design a compound point-wise reward assignment mechanism, which is composed of three types of rewards: the coverage reward, the execution reward and the redundancy reward, to learn a policy of SQL generation.•The compound reward performs well on the domain of SQL query learning.