2
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations

      Preprint
      , , , ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          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.

          Related collections

          Author and article information

          Journal
          02 June 2021
          Article
          2106.01093
          6dd8acb4-e76d-4f32-b144-dcab1dd55a6e

          http://arxiv.org/licenses/nonexclusive-distrib/1.0/

          History
          Custom metadata
          15 pages, 8 figures, accepted to ACL 2021 main conference
          cs.CL

          Theoretical computer science
          Theoretical computer science

          Comments

          Comment on this article