Semantic Parsing with Syntax- and Table-Aware SQL Generation

Yibo Sun, Duyu Tang, Nan Duan, Jianshu Ji, Guihong Cao, Xiaocheng Feng, Bing Qin, Ting Liu, Ming Zhou


Abstract
We present a generative model to map natural language questions into SQL queries. Existing neural network based approaches typically generate a SQL query word-by-word, however, a large portion of the generated results is incorrect or not executable due to the mismatch between question words and table contents. Our approach addresses this problem by considering the structure of table and the syntax of SQL language. The quality of the generated SQL query is significantly improved through (1) learning to replicate content from column names, cells or SQL keywords; and (2) improving the generation of WHERE clause by leveraging the column-cell relation. Experiments are conducted on WikiSQL, a recently released dataset with the largest question- SQL pairs. Our approach significantly improves the state-of-the-art execution accuracy from 69.0% to 74.4%.
Anthology ID:
P18-1034
Volume:
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2018
Address:
Melbourne, Australia
Editors:
Iryna Gurevych, Yusuke Miyao
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
361–372
Language:
URL:
https://aclanthology.org/P18-1034
DOI:
10.18653/v1/P18-1034
Bibkey:
Cite (ACL):
Yibo Sun, Duyu Tang, Nan Duan, Jianshu Ji, Guihong Cao, Xiaocheng Feng, Bing Qin, Ting Liu, and Ming Zhou. 2018. Semantic Parsing with Syntax- and Table-Aware SQL Generation. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 361–372, Melbourne, Australia. Association for Computational Linguistics.
Cite (Informal):
Semantic Parsing with Syntax- and Table-Aware SQL Generation (Sun et al., ACL 2018)
Copy Citation:
PDF:
https://aclanthology.org/P18-1034.pdf
Data
WikiSQLWikiTableQuestions