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.- Anthology ID:
- 2023.findings-acl.740
- Volume:
- Findings of the Association for Computational Linguistics: ACL 2023
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 11647–11654
- Language:
- URL:
- https://aclanthology.org/2023.findings-acl.740
- DOI:
- 10.18653/v1/2023.findings-acl.740
- Cite (ACL):
- Shuo Sun, Yuze Gao, Yuchen Zhang, Jian Su, Bin Chen, Yingzhan Lin, and Shuqi Sun. 2023. An Exploratory Study on Model Compression for Text-to-SQL. In Findings of the Association for Computational Linguistics: ACL 2023, pages 11647–11654, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- An Exploratory Study on Model Compression for Text-to-SQL (Sun et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/fix-volume-bibkeys/2023.findings-acl.740.pdf