V-SQL: A View-based Two-stage Text-to-SQL Framework
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929728513900544 |
|---|---|
| author | You, Zeshun Yao, Jiebin Cheng, Dong Wen, Zhiwei Lu, Zhiliang Shen, Xianyi |
| author_facet | You, Zeshun Yao, Jiebin Cheng, Dong Wen, Zhiwei Lu, Zhiliang Shen, Xianyi |
| contents | The text-to-SQL task aims to convert natural language into Structured Query Language (SQL) without bias. Recently, text-to-SQL methods based on large language models (LLMs) have garnered significant attention. The core of mainstream text-to-SQL frameworks is schema linking, which aligns user queries with relevant tables and columns in the database. Previous methods focused on schema linking while neglecting to enhance LLMs' understanding of database schema. The complex coupling relationships between tables in the database constrain the SQL generation capabilities of LLMs. To tackle this issue, this paper proposes a simple yet effective strategy called view-based schema. This strategy aids LLMs in understanding the database schema by decoupling tightly coupled tables into low-coupling views. We then introduce V-SQL, a view-based two-stage text-to-SQL framework. V-SQL involves the view-based schema strategy to enhance LLMs' understanding of database schema. Results on the authoritative datasets Bird indicate that V-SQL achieves competitive performance compared to existing state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15686 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | V-SQL: A View-based Two-stage Text-to-SQL Framework You, Zeshun Yao, Jiebin Cheng, Dong Wen, Zhiwei Lu, Zhiliang Shen, Xianyi Databases Computation and Language The text-to-SQL task aims to convert natural language into Structured Query Language (SQL) without bias. Recently, text-to-SQL methods based on large language models (LLMs) have garnered significant attention. The core of mainstream text-to-SQL frameworks is schema linking, which aligns user queries with relevant tables and columns in the database. Previous methods focused on schema linking while neglecting to enhance LLMs' understanding of database schema. The complex coupling relationships between tables in the database constrain the SQL generation capabilities of LLMs. To tackle this issue, this paper proposes a simple yet effective strategy called view-based schema. This strategy aids LLMs in understanding the database schema by decoupling tightly coupled tables into low-coupling views. We then introduce V-SQL, a view-based two-stage text-to-SQL framework. V-SQL involves the view-based schema strategy to enhance LLMs' understanding of database schema. Results on the authoritative datasets Bird indicate that V-SQL achieves competitive performance compared to existing state-of-the-art methods. |
| title | V-SQL: A View-based Two-stage Text-to-SQL Framework |
| topic | Databases Computation and Language |
| url | https://arxiv.org/abs/2502.15686 |