Question Generation from SQL Queries Improves Neural Semantic Parsing
arXiv:1808.06304
Abstract
We study how to learn a semantic parser of state-of-the-art accuracy with less supervised training data. We conduct our study on WikiSQL, the largest hand-annotated semantic parsing dataset to date. First, we demonstrate that question generation is an effective method that empowers us to learn a state-of-the-art neural network based semantic parser with thirty percent of the supervised training data. Second, we show that applying question generation to the full supervised training data further improves the state-of-the-art model. In addition, we observe that there is a logarithmic relationship between the accuracy of a semantic parser and the amount of training data.
arXiv commentThe paper will be presented in EMNLP 2018
References in corpus (19)
- Sequence to Sequence Learning with Neural Networks
- Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
- Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
- SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
- Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
- Incorporating Copying Mechanism in Sequence-to-Sequence Learning
- Question Answering and Question Generation as Dual Tasks
- Language to Logical Form with Neural Attention
- Compositional Semantic Parsing on Semi-Structured Tables
- Learning to Ask: Neural Question Generation for Reading Comprehension
- Learning Dependency-Based Compositional Semantics
- From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood
- Latent Variable Dialogue Models and their Diversity
- Semi-Supervised QA with Generative Domain-Adaptive Nets
- Learning to Paraphrase for Question Answering
- Semantic Parsing with Syntax- and Table-Aware SQL Generation
- Inferring Logical Forms From Denotations
- Two-Stage Synthesis Networks for Transfer Learning in Machine Comprehension
- Neural Multi-Step Reasoning for Question Answering on Semi-Structured Tables