End-to-End Cross-Domain Text-to-SQL Semantic Parsing with Auxiliary Task

TL;DR

This paper introduces a novel end-to-end cross-domain Text-to-SQL model that incorporates auxiliary tasks for schema linking and value filling, significantly improving accuracy especially when database contents are missing.

Contribution

It proposes a column selection auxiliary task and two value filling methods to enhance zero-shot semantic parsing in cross-domain Text-to-SQL tasks.

Findings

Improved execution accuracy on Spider dataset

Enhanced exact set match accuracy without database contents

Detailed analysis guiding future research

Abstract

In this work, we focus on two crucial components in the cross-domain text-to-SQL semantic parsing task: schema linking and value filling. To encourage the model to learn better encoding ability, we propose a column selection auxiliary task to empower the encoder with the relevance matching capability by using explicit learning targets. Furthermore, we propose two value filling methods to build the bridge from the existing zero-shot semantic parsers to real-world applications, considering most of the existing parsers ignore the values filling in the synthesized SQL. With experiments on Spider, our proposed framework improves over the baselines on the execution accuracy and exact set match accuracy when database contents are unavailable, and detailed analysis sheds light on future work.