LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations
This addresses the challenge of encoding complex graph structures for text-to-SQL tasks, which is incremental as it builds on prior node-centric methods by incorporating edge topology and relation distinctions.
The paper tackled the heterogeneous graph encoding problem in text-to-SQL by proposing LGESQL, which uses a line graph to efficiently propagate messages and integrate local and non-local relations, achieving state-of-the-art results of 62.8% with Glove and 72.0% with Electra on the Spider benchmark.
This work aims to tackle the challenging heterogeneous graph encoding problem in the text-to-SQL task. Previous methods are typically node-centric and merely utilize different weight matrices to parameterize edge types, which 1) ignore the rich semantics embedded in the topological structure of edges, and 2) fail to distinguish local and non-local relations for each node. To this end, we propose a Line Graph Enhanced Text-to-SQL (LGESQL) model to mine the underlying relational features without constructing meta-paths. By virtue of the line graph, messages propagate more efficiently through not only connections between nodes, but also the topology of directed edges. Furthermore, both local and non-local relations are integrated distinctively during the graph iteration. We also design an auxiliary task called graph pruning to improve the discriminative capability of the encoder. Our framework achieves state-of-the-art results (62.8% with Glove, 72.0% with Electra) on the cross-domain text-to-SQL benchmark Spider at the time of writing.