Learning to generate structured queries from natural language with indirect supervision. (May 2021)

• Record Type: Journal Article
• Authors: Bai, Ziwei; yu, Bo; Wu, Bowen; Wang, Zhuoran; Wang, Baoxun
• Is Part Of: Computer speech & language. Volume 67(2021)
• Publication Date: 2021-05
• Subjects: Structured query language -- Natural language understanding -- Reinforcement learning; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2020.101185
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: 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. Abstract: Generating structured query language (SQL) from natural language is an emerging research topic. This paper presents a new learning paradigm from indirect supervision of the answers to natural language questions, instead of SQL queries. This paradigm facilitates the acquisition of training data due to the abundant resources of question-answer pairs for various domains in the Internet, and expels the difficult SQL annotation job. An end-to-end neural model integrating with reinforcement learning is proposed to learn SQL generation policy within the answer-driven learning paradigm. The model is evaluated on datasets of different domains, including movie and academic publication. Experimental results show that our model outperforms the baseline models.