English

Question Generation from SQL Queries Improves Neural Semantic Parsing

Computation and Language 2018-08-28 v2

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.

Keywords

Cite

@article{arxiv.1808.06304,
  title  = {Question Generation from SQL Queries Improves Neural Semantic Parsing},
  author = {Daya Guo and Yibo Sun and Duyu Tang and Nan Duan and Jian Yin and Hong Chi and James Cao and Peng Chen and Ming Zhou},
  journal= {arXiv preprint arXiv:1808.06304},
  year   = {2018}
}

Comments

The paper will be presented in EMNLP 2018

R2 v1 2026-06-23T03:37:58.489Z