Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-22000
Full metadata record
DC FieldValueLanguage
dc.contributor.authorBrunner, Ursin-
dc.contributor.authorStockinger, Kurt-
dc.date.accessioned2021-03-14T11:35:30Z-
dc.date.available2021-03-14T11:35:30Z-
dc.date.issued2021-04-
dc.identifier.otherarXiv:2006.00888v2de_CH
dc.identifier.urihttps://digitalcollection.zhaw.ch/handle/11475/22000-
dc.description.abstractIn this paper we propose ValueNet light and ValueNet - two end-to-end Natural Language-to-SQL systems that incorporate values using the challenging Spider dataset.The main idea of our approach is to use not only metadata information from the underlying database but also information on the base data as input for our neural network architecture. In particular, we propose a novel architecture sketch to extract values from a user question and come up with possible value candidates which are not explicitly mentioned in the question. We then use a neural model based on an encoder-decoder architecture to synthesize the SQL query. Finally, we evaluate our model on the Spider challenge using the Execution Accuracy metric, a more difficult metric than used by most participants of the challenge. Our experimental evaluation demonstrates that ValueNet light and ValueNet reach state-of-the-art results of 67% and 62% accuracy, respectively, for translating from NL to SQL whilst incorporating values.de_CH
dc.language.isoende_CH
dc.publisherIEEEde_CH
dc.rightsNot specifiedde_CH
dc.subjectNL-to-SQLde_CH
dc.subjectNatural language interfacede_CH
dc.subjectNeural networkde_CH
dc.subjectTransformerde_CH
dc.subject.ddc005: Computerprogrammierung, Programme und Datende_CH
dc.titleValueNet : a natural language-to-SQL system that learns from database informationde_CH
dc.typeKonferenz: Paperde_CH
dcterms.typeTextde_CH
zhaw.departementSchool of Engineeringde_CH
zhaw.organisationalunitInstitut für Angewandte Informationstechnologie (InIT)de_CH
dc.identifier.doi10.21256/zhaw-22000-
zhaw.conference.detailsInternational Conference on Data Engineering (ICDE), Chania, Greece, 19-22 April 2021de_CH
zhaw.funding.euinfo:eu-repo/grantAgreement/EC/H2020/863410//INODE - Intelligent Open Data Exploration/INODEde_CH
zhaw.originated.zhawYesde_CH
zhaw.publication.statusupdatedVersionde_CH
zhaw.publication.reviewPeer review (Publikation)de_CH
zhaw.title.proceedingsProceedings of the 37th ICDEde_CH
zhaw.webfeedDatalabde_CH
zhaw.webfeedInformation Engineeringde_CH
zhaw.funding.zhawINODE - Intelligent Open Data Explorationde_CH
zhaw.author.additionalNode_CH
zhaw.display.portraitYesde_CH
Appears in collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
2021_Brunner-Stockinger_ValueNet_ICDE-Paper.pdf585.22 kBAdobe PDFThumbnail
View/Open
Show simple item record
Brunner, U., & Stockinger, K. (2021, April). ValueNet : a natural language-to-SQL system that learns from database information. Proceedings of the 37th ICDE. https://doi.org/10.21256/zhaw-22000
Brunner, U. and Stockinger, K. (2021) ‘ValueNet : a natural language-to-SQL system that learns from database information’, in Proceedings of the 37th ICDE. IEEE. Available at: https://doi.org/10.21256/zhaw-22000.
U. Brunner and K. Stockinger, “ValueNet : a natural language-to-SQL system that learns from database information,” in Proceedings of the 37th ICDE, Apr. 2021. doi: 10.21256/zhaw-22000.
BRUNNER, Ursin und Kurt STOCKINGER, 2021. ValueNet : a natural language-to-SQL system that learns from database information. In: Proceedings of the 37th ICDE. Conference paper. IEEE. April 2021
Brunner, Ursin, and Kurt Stockinger. 2021. “ValueNet : A Natural Language-to-SQL System That Learns from Database Information.” Conference paper. In Proceedings of the 37th ICDE. IEEE. https://doi.org/10.21256/zhaw-22000.
Brunner, Ursin, and Kurt Stockinger. “ValueNet : A Natural Language-to-SQL System That Learns from Database Information.” Proceedings of the 37th ICDE, IEEE, 2021, https://doi.org/10.21256/zhaw-22000.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.