Improved NL2SQL based on Multi-layer Expert Network

TL;DR

This paper presents MLEG-SQL, a hierarchical multi-layer expert network that improves natural language to SQL translation accuracy by addressing task conflict issues in multi-task learning.

Contribution

It introduces a novel multi-layer hierarchical network architecture for NL2SQL that reduces negative transfer and enhances SQL generation accuracy.

Findings

Effective on WiKSQL dataset

Reduces negative migration issues

Improves SQL accuracy

Abstract

The Natural Language to SQL (NL2SQL) technique is used to convert natural language queries into executable SQL statements. Typically, slot-filling is employed as a classification method for multi-task cases to achieve this goal. However, slot-filling can result in inaccurate SQL statement generation due to negative migration issues arising from different classification tasks. To overcome this limitation, this study introduces a new approach called Multi-Layer Expert Generate SQL (MLEG-SQL), which utilizes a dedicated multi-task hierarchical network. The lower layer of the network extracts semantic features of natural language statements, while the upper layer builds a specialized expert system for handling specific classification tasks. This hierarchical approach mitigates performance degradation resulting from different task conflicts. The proposed method was evaluated on the WiKSQL dataset and was found to be effective in generating accurate SQL statements.