English

Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing

Computation and Language 2021-01-01 v2 Artificial Intelligence Databases Machine Learning

Abstract

We present BRIDGE, a powerful sequential architecture for modeling dependencies between natural language questions and relational databases in cross-DB semantic parsing. BRIDGE represents the question and DB schema in a tagged sequence where a subset of the fields are augmented with cell values mentioned in the question. The hybrid sequence is encoded by BERT with minimal subsequent layers and the text-DB contextualization is realized via the fine-tuned deep attention in BERT. Combined with a pointer-generator decoder with schema-consistency driven search space pruning, BRIDGE attained state-of-the-art performance on popular cross-DB text-to-SQL benchmarks, Spider (71.1\% dev, 67.5\% test with ensemble model) and WikiSQL (92.6\% dev, 91.9\% test). Our analysis shows that BRIDGE effectively captures the desired cross-modal dependencies and has the potential to generalize to more text-DB related tasks. Our implementation is available at \url{https://github.com/salesforce/TabularSemanticParsing}.

Keywords

Cite

@article{arxiv.2012.12627,
  title  = {Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing},
  author = {Xi Victoria Lin and Richard Socher and Caiming Xiong},
  journal= {arXiv preprint arXiv:2012.12627},
  year   = {2021}
}

Comments

EMNLP Findings 2020 long paper extended; 23 pages

R2 v1 2026-06-23T21:17:04.149Z