Re-examining the Role of Schema Linking in Text-to-SQL

Wenqiang Lei, Weixin Wang, Zhixin Ma, Tian Gan, Wei Lu, Min-Yen Kan, Tat-Seng Chua


Abstract
In existing sophisticated text-to-SQL models, schema linking is often considered as a simple, minor component, belying its importance. By providing a schema linking corpus based on the Spider text-to-SQL dataset, we systematically study the role of schema linking. We also build a simple BERT-based baseline, called Schema-Linking SQL (SLSQL) to perform a data-driven study. We find when schema linking is done well, SLSQL demonstrates good performance on Spider despite its structural simplicity. Many remaining errors are attributable to corpus noise. This suggests schema linking is the crux for the current text-to-SQL task. Our analytic studies provide insights on the characteristics of schema linking for future developments of text-to-SQL tasks.
Anthology ID:
2020.emnlp-main.564
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6943–6954
Language:
URL:
https://aclanthology.org/2020.emnlp-main.564
DOI:
10.18653/v1/2020.emnlp-main.564
Bibkey:
Cite (ACL):
Wenqiang Lei, Weixin Wang, Zhixin Ma, Tian Gan, Wei Lu, Min-Yen Kan, and Tat-Seng Chua. 2020. Re-examining the Role of Schema Linking in Text-to-SQL. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6943–6954, Online. Association for Computational Linguistics.
Cite (Informal):
Re-examining the Role of Schema Linking in Text-to-SQL (Lei et al., EMNLP 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.emnlp-main.564.pdf
Video:
 https://slideslive.com/38939387