Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization

Yujian Gan, Xinyun Chen, Matthew Purver


Abstract
Recently, there has been significant progress in studying neural networks for translating text descriptions into SQL queries under the zero-shot cross-domain setting. Despite achieving good performance on some public benchmarks, we observe that existing text-to-SQL models do not generalize when facing domain knowledge that does not frequently appear in the training data, which may render the worse prediction performance for unseen domains. In this work, we investigate the robustness of text-to-SQL models when the questions require rarely observed domain knowledge. In particular, we define five types of domain knowledge and introduce Spider-DK (DK is the abbreviation of domain knowledge), a human-curated dataset based on the Spider benchmark for text-to-SQL translation. NL questions in Spider-DK are selected from Spider, and we modify some samples by adding domain knowledge that reflects real-world question paraphrases. We demonstrate that the prediction accuracy dramatically drops on samples that require such domain knowledge, even if the domain knowledge appears in the training set, and the model provides the correct predictions for related training samples.
Anthology ID:
2021.emnlp-main.702
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8926–8931
Language:
URL:
https://aclanthology.org/2021.emnlp-main.702
DOI:
10.18653/v1/2021.emnlp-main.702
Bibkey:
Cite (ACL):
Yujian Gan, Xinyun Chen, and Matthew Purver. 2021. Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8926–8931, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization (Gan et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.702.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.702.mp4
Code
 ygan/spider-dk
Data
Spider-Realistic