File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: TypeSQL: Knowledge-based type-aware neural text-to-SQL generation

TitleTypeSQL: Knowledge-based type-aware neural text-to-SQL generation
Authors
Yu, TaoLi, ZifanZhang, ZilinZhang, RuiRadev, Dragomir
Issue Date2018
Citation
2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2018), New Orleans, LA, 1-6 June 2018. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), 2018, p. 588-594 How to Cite?
DOI: http://dx.doi.org/10.18653/v1/N18-2093
AbstractInteracting with relational databases through natural language helps users of any background easily query and analyze a vast amount of data. This requires a system that understands users' questions and converts them to SQL queries automatically. In this paper we present a novel approach, TYPESQL, which views this problem as a slot filling task. Additionally, TYPESQL utilizes type information to better understand rare entities and numbers in natural language questions. We test this idea on the WikiSQL dataset and outperform the prior state-of-the-art by 5.5% in much less time. We also show that accessing the content of databases can significantly improve the performance when users' queries are not wellformed. TYPESQL gets 82.6% accuracy, a 17.5% absolute improvement compared to the previous content-sensitive model.
Persistent Identifierhttp://hdl.handle.net/10722/303624

 

DC FieldValueLanguage
dc.contributor.authorYu, Tao-
dc.contributor.authorLi, Zifan-
dc.contributor.authorZhang, Zilin-
dc.contributor.authorZhang, Rui-
dc.contributor.authorRadev, Dragomir-
dc.date.accessioned2021-09-15T08:25:41Z-
dc.date.available2021-09-15T08:25:41Z-
dc.date.issued2018-
dc.identifier.citation2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2018), New Orleans, LA, 1-6 June 2018. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), 2018, p. 588-594-
dc.identifier.urihttp://hdl.handle.net/10722/303624-
dc.description.abstractInteracting with relational databases through natural language helps users of any background easily query and analyze a vast amount of data. This requires a system that understands users' questions and converts them to SQL queries automatically. In this paper we present a novel approach, TYPESQL, which views this problem as a slot filling task. Additionally, TYPESQL utilizes type information to better understand rare entities and numbers in natural language questions. We test this idea on the WikiSQL dataset and outperform the prior state-of-the-art by 5.5% in much less time. We also show that accessing the content of databases can significantly improve the performance when users' queries are not wellformed. TYPESQL gets 82.6% accuracy, a 17.5% absolute improvement compared to the previous content-sensitive model.-
dc.languageeng-
dc.relation.ispartofProceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)-
dc.rightsThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.-
dc.titleTypeSQL: Knowledge-based type-aware neural text-to-SQL generation-
dc.typeConference_Paper-
dc.description.naturepublished_or_final_version-
dc.identifier.doi10.18653/v1/N18-2093-
dc.identifier.scopuseid_2-s2.0-85072866387-
dc.identifier.spage588-
dc.identifier.epage594-

Export via OAI-PMH Interface in XML Formats

OR

Export to Other Non-XML Formats