Abstract
Most deep learning approaches for text-to-SQL generation are limited to the WikiSQL dataset, which only supports very simple queries over a single table. We focus on the Spider dataset, a complex and cross-domain text-to-SQL task, which includes complex queries over multiple tables. In this paper, we propose a SQL clause-wise decoding neural architecture with a self-attention based database schema encoder to address the Spider task. Each of the clause-specific decoders consists of a set of sub-modules, which is defined by the syntax of each clause. Additionally, our model works recursively to support nested queries. When evaluated on the Spider dataset, our approach achieves 4.6% and 9.8% accuracy gain in the test and dev sets, respectively. In addition, we show that our model is significantly more effective at predicting complex and nested queries than previous work.- Anthology ID:
- D19-1624
- Volume:
- Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Editors:
- Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
- Venues:
- EMNLP | IJCNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6045–6051
- Language:
- URL:
- https://aclanthology.org/D19-1624
- DOI:
- 10.18653/v1/D19-1624
- Cite (ACL):
- Dongjun Lee. 2019. Clause-Wise and Recursive Decoding for Complex and Cross-Domain Text-to-SQL Generation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 6045–6051, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Clause-Wise and Recursive Decoding for Complex and Cross-Domain Text-to-SQL Generation (Lee, EMNLP-IJCNLP 2019)
- PDF:
- https://preview.aclanthology.org/naacl24-info/D19-1624.pdf
- Data
- WikiSQL