Skip to main navigation Skip to search Skip to main content

Graph enhanced cross-domain text-to-SQL generation

  • Siyu Huo
  • , Tengfei Ma
  • , Jie Chen
  • , Maria Chang
  • , Lingfei Wu
  • , Michael Witbrock
  • IBM
  • MIT-IBM Watson AI Lab
  • The University of Auckland

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

9 Scopus citations

Abstract

Semantic parsing is a fundamental problem in natural language understanding, as it involves the mapping of natural language to structured forms such as executable queries or logic-like knowledge representations. Existing deep learning approaches for semantic parsing have shown promise on a variety of benchmark data sets, particularly on textto- SQL parsing. However, most text-to-SQL parsers do not generalize to unseen data sets in different domains. In this paper, we propose a new cross-domain learning scheme to perform text-to-SQL translation and demonstrate its use on Spider, a large-scale cross-domain text-to-SQL data set. We improve upon a state-of-the-art Spider model, SyntaxSQLNet, by constructing a graph of column names for all databases and using graph neural networks to compute their embeddings. The resulting embeddings offer better cross-domain representations and SQL queries, as evidenced by substantial improvement on the Spider data set compared to SyntaxSQLNet.

Original languageEnglish
Title of host publicationEMNLP-IJCNLP 2019 - Graph-Based Methods for Natural Language Processing - Proceedings of the 13th Workshop
PublisherAssociation for Computational Linguistics (ACL)
Pages159-163
Number of pages5
ISBN (Electronic)9781950737864
StatePublished - 2019
Event13th Workshop on Graph-Based Methods for Natural Language Processing, TextGraphs 2019, in conjunction with the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019 - Hong Kong, Hong Kong
Duration: Nov 4 2019Nov 4 2019

Publication series

NameEMNLP-IJCNLP 2019 - Graph-Based Methods for Natural Language Processing - Proceedings of the 13th Workshop

Conference

Conference13th Workshop on Graph-Based Methods for Natural Language Processing, TextGraphs 2019, in conjunction with the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, EMNLP-IJCNLP 2019
Country/TerritoryHong Kong
CityHong Kong
Period11/4/1911/4/19

Fingerprint

Dive into the research topics of 'Graph enhanced cross-domain text-to-SQL generation'. Together they form a unique fingerprint.

Cite this