Addressing Limitations of Encoder-Decoder Based Approach to Text-to-SQL
Octavian Popescu, Irene Manotas, Ngoc Phuoc An Vo, Hangu Yeo, Elahe Khorashani, Vadim Sheinin
Abstract
Most attempts on Text-to-SQL task using encoder-decoder approach show a big problem of dramatic decline in performance for new databases. For the popular Spider dataset, despite models achieving 70% accuracy on its development or test sets, the same models show a huge decline below 20% accuracy for unseen databases. The root causes for this problem are complex and they cannot be easily fixed by adding more manually created training. In this paper we address the problem and propose a solution that is a hybrid system using automated training-data augmentation technique. Our system consists of a rule-based and a deep learning components that interact to understand crucial information in a given query and produce correct SQL as a result. It achieves double-digit percentage improvement for databases that are not part of the Spider corpus.
BibTeX
@inproceedings{popescu-etal-2022-addressing,
title = "Addressing Limitations of Encoder-Decoder Based Approach to Text-to-{SQL}",
author = "Popescu, Octavian and
Manotas, Irene and
Vo, Ngoc Phuoc An and
Yeo, Hangu and
Khorashani, Elahe and
Sheinin, Vadim",
editor = "Calzolari, Nicoletta and
Huang, Chu-Ren and
Kim, Hansaem and
Pustejovsky, James and
Wanner, Leo and
Choi, Key-Sun and
Ryu, Pum-Mo and
Chen, Hsin-Hsi and
Donatelli, Lucia and
Ji, Heng and
Kurohashi, Sadao and
Paggio, Patrizia and
Xue, Nianwen and
Kim, Seokhwan and
Hahm, Younggyun and
He, Zhong and
Lee, Tony Kyungil and
Santus, Enrico and
Bond, Francis and
Na, Seung-Hoon",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.137/",
pages = "1593--1603"
}