Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions

TL;DR

This paper introduces an editing-based approach for cross-domain context-dependent text-to-SQL generation, leveraging previous query edits and table-aware encoding to improve accuracy over state-of-the-art methods.

Contribution

It proposes a novel editing mechanism that reuses previous SQL tokens, combined with an utterance-table encoder and table-aware decoder for better cross-domain performance.

Findings

Outperforms state-of-the-art baselines on SParC dataset

Utilizes query editing to improve generation quality

Demonstrates robustness to error propagation

Abstract

We focus on the cross-domain context-dependent text-to-SQL generation task. Based on the observation that adjacent natural language questions are often linguistically dependent and their corresponding SQL queries tend to overlap, we utilize the interaction history by editing the previous predicted query to improve the generation quality. Our editing mechanism views SQL as sequences and reuses generation results at the token level in a simple manner. It is flexible to change individual tokens and robust to error propagation. Furthermore, to deal with complex table structures in different domains, we employ an utterance-table encoder and a table-aware decoder to incorporate the context of the user utterance and the table schema. We evaluate our approach on the SParC dataset and demonstrate the benefit of editing compared with the state-of-the-art baselines which generate SQL from scratch. Our code is available at https://github.com/ryanzhumich/sparc_atis_pytorch.