An Exploratory Study on Model Compression for Text-to-SQL
Shuo Sun, Yuze Gao, Yuchen Zhang, Jian Su, Bin Chen, Yingzhan Lin, Shuqi Sun
Abstract
Text-to-SQL translates user queries into SQL statements that can retrieve relevant answers from relational databases. Recent approaches to Text-to-SQL rely on pre-trained language models that are computationally expensive and technically challenging to deploy in real-world applications that require real-time or on-device processing capabilities. In this paper, we perform a focused study on the feasibility of applying recent model compression techniques to sketch-based and sequence-to-sequence Text-to-SQL models. Our results reveal that sketch-based Text-to-SQL models generally have higher inference efficiency and respond better to model compression than sequence-to-sequence models, making them ideal for real-world deployments, especially in use cases with simple SQL statements.
BibTeX
@inproceedings{sun-etal-2023-exploratory,
title = "An Exploratory Study on Model Compression for Text-to-{SQL}",
author = "Sun, Shuo and
Gao, Yuze and
Zhang, Yuchen and
Su, Jian and
Chen, Bin and
Lin, Yingzhan and
Sun, Shuqi",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.740/",
doi = "10.18653/v1/2023.findings-acl.740",
pages = "11647--11654"
}