IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generation

TL;DR

This paper introduces IGSQL, a neural model that leverages a database schema interaction graph to improve context-dependent text-to-SQL generation, outperforming previous models on benchmark datasets.

Contribution

The paper proposes a novel database schema interaction graph encoder and a gate mechanism, enhancing context-aware SQL generation beyond previous approaches.

Findings

Outperforms previous state-of-the-art models on SParC and CoSQL datasets.

Demonstrates the effectiveness of the schema interaction graph encoder.

Ablation studies confirm the contribution of each component.

Abstract

Context-dependent text-to-SQL task has drawn much attention in recent years. Previous models on context-dependent text-to-SQL task only concentrate on utilizing historical user inputs. In this work, in addition to using encoders to capture historical information of user inputs, we propose a database schema interaction graph encoder to utilize historicalal information of database schema items. In decoding phase, we introduce a gate mechanism to weigh the importance of different vocabularies and then make the prediction of SQL tokens. We evaluate our model on the benchmark SParC and CoSQL datasets, which are two large complex context-dependent cross-domain text-to-SQL datasets. Our model outperforms previous state-of-the-art model by a large margin and achieves new state-of-the-art results on the two datasets. The comparison and ablation results demonstrate the efficacy of our model and the usefulness of the database schema interaction graph encoder.