DBCopilot: Natural Language Querying over Massive Databases via Schema Routing

2023-12-06

AI Summary

Existing approaches to NL2SQL for large-scale databases suffer from limited cross-database schema routing accuracy and suboptimal inference efficiency. To address these challenges, this paper proposes a decoupled architecture: first, a relation-aware differentiable search index enabling lightweight, end-to-end trainable schema routing; second, a reverse schema-to-question generation mechanism that self-adaptively trains the router without requiring annotated supervision. By explicitly separating schema routing from SQL generation, our framework achieves unsupervised, zero-shot cross-database querying—the first such approach in the literature. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art baselines in both execution accuracy and inference speed, while exhibiting strong scalability and deployment robustness across diverse database schemas.

Abstract

The development of Natural Language Interfaces to Databases (NLIDBs) has been greatly advanced by the advent of large language models (LLMs), which provide an intuitive way to translate natural language (NL) questions into Structured Query Language (SQL) queries. While significant progress has been made in LLM-based NL2SQL, existing approaches face several challenges in real-world scenarios of natural language querying over massive databases. In this paper, we present DBCopilot, a framework that addresses these challenges by employing a compact and flexible copilot model for routing over massive databases. Specifically, DBCopilot decouples schema-agnostic NL2SQL into schema routing and SQL generation. This framework utilizes a single lightweight differentiable search index to construct semantic mappings for massive database schemata, and navigates natural language questions to their target databases and tables in a relation-aware joint retrieval manner. The routed schemata and questions are then fed into LLMs for effective SQL generation. Furthermore, DBCopilot introduces a reverse schema-to-question generation paradigm that can automatically learn and adapt the router over massive databases without manual intervention. Experimental results verify that DBCopilot is a scalable and effective solution for schema-agnostic NL2SQL, providing a significant advance in handling natural language querying over massive databases for NLIDBs.

Problem

• Enhances natural language querying over massive databases
• Decouples schema-agnostic NL2SQL into schema routing
• Introduces reverse schema-to-question generation paradigm

Innovation

• Schema routing for massive databases
• Lightweight semantic mapping construction
• Reverse schema-to-question learning