Skeletons Matter: Dynamic Data Augmentation for Text-to-Query

TL;DR

This paper introduces a dynamic data augmentation framework for Text-to-Query tasks, leveraging query skeletons to improve semantic parsing across multiple query languages with minimal data, achieving state-of-the-art results.

Contribution

It unifies semantic parsing across various query languages and proposes a skeleton-focused augmentation method that enhances model performance efficiently.

Findings

Achieves state-of-the-art results on four benchmarks.

Uses only a small amount of synthesized data.

Demonstrates the generality and efficiency of the approach.

Abstract

The task of translating natural language questions into query languages has long been a central focus in semantic parsing. Recent advancements in Large Language Models (LLMs) have significantly accelerated progress in this field. However, existing studies typically focus on a single query language, resulting in methods with limited generalizability across different languages. In this paper, we formally define the Text-to-Query task paradigm, unifying semantic parsing tasks across various query languages. We identify query skeletons as a shared optimization target of Text-to-Query tasks, and propose a general dynamic data augmentation framework that explicitly diagnoses model-specific weaknesses in handling these skeletons to synthesize targeted training data. Experiments on four Text-to-Query benchmarks demonstrate that our method achieves state-of-the-art performance using only a small amount of synthesized data, highlighting the efficiency and generality of our approach and laying a solid foundation for unified research on Text-to-Query tasks. We release our code at https://github.com/jjjycaptain/Skeletron.