TSCL-SQL: Two-Stage Curriculum Learning Framework for Text-to-SQL  

作　　者：尹枫 程路易 王秋月 王志军 杜明 徐波 YIN Feng;CHENG Luyi;WANG Qiuyue;WANG Zhijun;DU Ming;XU Bo(School of Computer Science and Technology,Donghua University,Shanghai 201620,China)

机构地区：[1]School of Computer Science and Technology,Donghua University,Shanghai 201620,China

出　　处：《Journal of Donghua University(English Edition)》2023年第4期421-427,共7页东华大学学报（英文版）

基　　金：Fundamental Research Funds for the Central Universities,China (No. 2232023D-19)。

摘　　要：Text-to-SQL is the task of translating a natural language query into a structured query language. Existing text-to-SQL approaches focus on improving the model’s architecture while ignoring the relationship between queries and table schemas and the differences in difficulty between examples in the dataset. To tackle these challenges, a two-stage curriculum learning framework for text-to-SQL(TSCL-SQL) is proposed in this paper. To exploit the relationship between the queries and the table schemas, a schema identification pre-training task is proposed to make the model choose the correct table schema from a set of candidates for a specific query. To leverage the differences in difficulty between examples, curriculum learning is applied to the text-to-SQL task, accompanied by an automatic curriculum learning solution, including a difficulty scorer and a training scheduler. Experiments show that the framework proposed in this paper is effective.

关 键 词：text-to-SQL curriculum learning semantic parsing 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]