RECPARSER: A Recursive Semantic Parsing Framework for Text-to-SQL Task
Abstract
Neural semantic parsers usually fail to parse long and complicated utterances into nested SQL queries, due to the large search space. In this paper, we propose a novel recursive semantic parsing framework called RECPARSER to generate the nested SQL query layer-by-layer. It decomposes the complicated nested SQL query generation problem into several progressive non-nested SQL query generation problems. Furthermore, we propose a novel Question Decomposer module to explicitly encourage RECPARSER to focus on different components of an utterance when predicting SQL queries of different layers. Experiments on the Spider dataset show that our approach is more effective compared to the previous works at predicting the nested SQL queries. In addition, we achieve an overall accuracy that is comparable with state-of-the-art approaches.
Cite
Text
Zeng et al. "RECPARSER: A Recursive Semantic Parsing Framework for Text-to-SQL Task." International Joint Conference on Artificial Intelligence, 2020. doi:10.24963/IJCAI.2020/504Markdown
[Zeng et al. "RECPARSER: A Recursive Semantic Parsing Framework for Text-to-SQL Task." International Joint Conference on Artificial Intelligence, 2020.](https://mlanthology.org/ijcai/2020/zeng2020ijcai-recparser/) doi:10.24963/IJCAI.2020/504BibTeX
@inproceedings{zeng2020ijcai-recparser,
title = {{RECPARSER: A Recursive Semantic Parsing Framework for Text-to-SQL Task}},
author = {Zeng, Yu and Gao, Yan and Guo, Jiaqi and Chen, Bei and Liu, Qian and Lou, Jian-Guang and Teng, Fei and Zhang, Dongmei},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2020},
pages = {3644-3650},
doi = {10.24963/IJCAI.2020/504},
url = {https://mlanthology.org/ijcai/2020/zeng2020ijcai-recparser/}
}