The Interpretability Analysis of the Model Can Bring Improvements to the Text-to-SQL Task

TL;DR

This paper combines interpretability analysis with execution-guided strategies and model fusion to improve text-to-SQL performance, especially in predicting WHERE clause conditions, reducing reliance on labeled data.

Contribution

It introduces the CESQL model that integrates interpretability and execution-guided techniques to enhance accuracy in text-to-SQL tasks without extensive labeled data.

Findings

Significant accuracy boost on WikiSQL dataset

Reduced dependence on labeled condition data

Effective handling of basic database queries

Abstract

To elevate the foundational capabilities and generalization prowess of the text-to-SQL model in real-world applications, we integrate model interpretability analysis with execution-guided strategy for semantic parsing of WHERE clauses in SQL queries. Furthermore, we augment this approach with filtering adjustments, logical correlation refinements, and model fusion, culminating in the design of the CESQL model that facilitates conditional enhancement. Our model excels on the WikiSQL dataset, which is emblematic of single-table database query tasks, markedly boosting the accuracy of prediction outcomes. When predicting conditional values in WHERE clauses, we have not only minimized our dependence on data within the condition columns of tables but also circumvented the impact of manually labeled training data. Our hope is that this endeavor to enhance accuracy in processing basic database queries will offer fresh perspectives for research into handling complex queries and scenarios featuring irregular data in real-world database environments.