SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers

Bowen Qin, Lihan Wang, Binyuan Hui, Bowen Li, Xiangpeng Wei, Binhua Li, Fei Huang, Luo Si, Min Yang, Yongbin Li


Abstract
This paper aims to improve the performance of text-to-SQL parsing by exploring the intrinsic uncertainties in the neural network based approaches (called SUN). From the data uncertainty perspective, it is indisputable that a single SQL can be learned from multiple semantically-equivalent questions. Different from previous methods that are limited to one-to-one mapping, we propose a data uncertainty constraint to explore the underlying complementary semantic information among multiple semantically-equivalent questions (many-to-one) and learn the robust feature representations with reduced spurious associations. In this way, we can reduce the sensitivity of the learned representations and improve the robustness of the parser. From the model uncertainty perspective, there is often structural information (dependence) among the weights of neural networks. To improve the generalizability and stability of neural text-to-SQL parsers, we propose a model uncertainty constraint to refine the query representations by enforcing the output representations of different perturbed encoding networks to be consistent with each other. Extensive experiments on five benchmark datasets demonstrate that our method significantly outperforms strong competitors and achieves new state-of-the-art results.
Anthology ID:
2022.coling-1.471
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
5298–5308
Language:
URL:
https://aclanthology.org/2022.coling-1.471
DOI:
Bibkey:
Cite (ACL):
Bowen Qin, Lihan Wang, Binyuan Hui, Bowen Li, Xiangpeng Wei, Binhua Li, Fei Huang, Luo Si, Min Yang, and Yongbin Li. 2022. SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers. In Proceedings of the 29th International Conference on Computational Linguistics, pages 5298–5308, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers (Qin et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.471.pdf
Code
 alibabaresearch/damo-convai