Conversing with databases: Practical Natural Language Querying

Denis Kochedykov, Fenglin Yin, Sreevidya Khatravath


Abstract
In this work, we designed, developed and released in production DataQue – a hybrid NLQ (Natural Language Querying) system for conversational DB querying. We address multiple practical problems that are not accounted for in public Text-to-SQL solutions – numerous complex implied conditions in user questions, jargon and abbreviations, custom calculations, non-SQL operations, a need to inject all those into pipeline fast and to have guaranteed parsing results for demanding users, cold-start problem. The DataQue processing pipeline for Text-to-SQL translation consists of 10-15 model-based and rule-based components that allows to tightly control the processing.
Anthology ID:
2023.emnlp-industry.36
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
Month:
December
Year:
2023
Address:
Singapore
Editors:
Mingxuan Wang, Imed Zitouni
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
372–379
Language:
URL:
https://aclanthology.org/2023.emnlp-industry.36
DOI:
10.18653/v1/2023.emnlp-industry.36
Bibkey:
Cite (ACL):
Denis Kochedykov, Fenglin Yin, and Sreevidya Khatravath. 2023. Conversing with databases: Practical Natural Language Querying. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 372–379, Singapore. Association for Computational Linguistics.
Cite (Informal):
Conversing with databases: Practical Natural Language Querying (Kochedykov et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-industry.36.pdf
Video:
 https://aclanthology.org/2023.emnlp-industry.36.mp4