Photon: A Robust Cross-Domain Text-to-SQL System

Jichuan Zeng, Xi Victoria Lin, Steven C.H. Hoi, Richard Socher, Caiming Xiong, Michael Lyu, Irwin King


Abstract
Natural language interfaces to databases(NLIDB) democratize end user access to relational data. Due to fundamental differences between natural language communication and programming, it is common for end users to issue questions that are ambiguous to the system or fall outside the semantic scope of its underlying query language. We present PHOTON, a robust, modular, cross-domain NLIDB that can flag natural language input to which a SQL mapping cannot be immediately determined. PHOTON consists of a strong neural semantic parser (63.2% structure accuracy on the Spider dev benchmark), a human-in-the-loop question corrector, a SQL executor and a response generator. The question corrector isa discriminative neural sequence editor which detects confusion span(s) in the input question and suggests rephrasing until a translatable input is given by the user or a maximum number of iterations are conducted. Experiments on simulated data show that the proposed method effectively improves the robustness of text-to-SQL system against untranslatable user input.The live demo of our system is available at http://www.naturalsql.com
Anthology ID:
2020.acl-demos.24
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
204–214
Language:
URL:
https://aclanthology.org/2020.acl-demos.24
DOI:
10.18653/v1/2020.acl-demos.24
Bibkey:
Cite (ACL):
Jichuan Zeng, Xi Victoria Lin, Steven C.H. Hoi, Richard Socher, Caiming Xiong, Michael Lyu, and Irwin King. 2020. Photon: A Robust Cross-Domain Text-to-SQL System. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 204–214, Online. Association for Computational Linguistics.
Cite (Informal):
Photon: A Robust Cross-Domain Text-to-SQL System (Zeng et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-demos.24.pdf
Video:
 http://slideslive.com/38928624
Data
CoSQL