Service-oriented Text-to-SQL Parsing

Wangsu Hu, Jilei Tian


Abstract
The information retrieval from relational database requires professionals who has an understanding of structural query language such as SQL. TEXT2SQL models apply natural language inference to enable user interacting the database via natural language utterance. Current TEXT2SQL models normally focus on generating complex SQL query in a precise and complete fashion while certain features of real-world application in the production environment is not fully addressed. This paper is aimed to develop a service-oriented Text-to-SQL parser that translates natural language utterance to structural and executable SQL query. We introduce a algorithmic framework named Semantic-Enriched SQL generator (SE-SQL) that enables flexibly access database than rigid API in the application while keeping the performance quality for the most commonly used cases. The qualitative result shows that the proposed model achieves 88.3% execution accuracy on WikiSQL task, outperforming baseline by 13% error reduction. Moreover, the framework considers several service-oriented needs including low-complexity inference, out-of-table rejection, and text normalization.
Anthology ID:
2020.findings-emnlp.201
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2020
Month:
November
Year:
2020
Address:
Online
Editors:
Trevor Cohn, Yulan He, Yang Liu
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2218–2222
Language:
URL:
https://aclanthology.org/2020.findings-emnlp.201
DOI:
10.18653/v1/2020.findings-emnlp.201
Bibkey:
Cite (ACL):
Wangsu Hu and Jilei Tian. 2020. Service-oriented Text-to-SQL Parsing. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 2218–2222, Online. Association for Computational Linguistics.
Cite (Informal):
Service-oriented Text-to-SQL Parsing (Hu & Tian, Findings 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/proper-vol2-ingestion/2020.findings-emnlp.201.pdf
Optional supplementary material:
 2020.findings-emnlp.201.OptionalSupplementaryMaterial.pdf
Data
WikiSQL