Learning to Generate Structured Queries from Natural Language with Indirect Supervision
arXiv:1809.03195
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.
11 pages, 4 figures
References in corpus (8)
- Sequence to Sequence Learning with Neural Networks
- Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
- Dynamic Coattention Networks For Question Answering
- SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
- Incorporating Copying Mechanism in Sequence-to-Sequence Learning
- Modeling Coverage for Neural Machine Translation
- Compositional Semantic Parsing on Semi-Structured Tables
- From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood