Decoupling SQL Query Hardness Parsing for Text-to-SQL
Jiawen Yi, Guo Chen
TL;DR
The paper presents a pair of LaTeX class files, cas-sc.cls and cas-dc.cls, that support single- and double-column layouts for Elsevier journal submissions. Through a comprehensive Usage section, it explains how to enable long front matter, customize author blocks and affiliations, and place the abstract and keywords using dedicated environments. These features aim to streamline manuscript preparation and improve compatibility with electronic submission workflows. By standardizing front matter and layout options, the template reduces formatting overhead and helps authors meet publisher requirements.
Abstract
The fundamental goal of the Text-to-SQL task is to translate natural language question into SQL query. Current research primarily emphasizes the information coupling between natural language questions and schemas, and significant progress has been made in this area. The natural language questions as the primary task requirements source determines the hardness of correspond SQL queries, the correlation between the two always be ignored. However, when the correlation between questions and queries was decoupled, it may simplify the task. In this paper, we introduce an innovative framework for Text-to-SQL based on decoupling SQL query hardness parsing. This framework decouples the Text-to-SQL task based on query hardness by analyzing questions and schemas, simplifying the multi-hardness task into a single-hardness challenge. This greatly reduces the parsing pressure on the language model. We evaluate our proposed framework and achieve a new state-of-the-art performance of fine-turning methods on Spider dev.