DBPal: a Novel lightweight NL2SQL training pipeline

  • NATURAL LANGUAGE (NL) IS A PROMISING ALTERNATIVE INTERFACE TO DATABASE MANAGEMENT SYSTEMS (DBMSs) BECAUSE IT ENABLES NON-TECHNICAL USERS TO FORMULATE COMPLEX QUESTIONS. RECENTLY, DEEP LEARNING HAS GAINED TRACTION FOR TRANSLATING NATURAL LANGUAGE TO SQL. HOWEVER, THE CORE PROBLEM WITH EXISTING DEEP LEARNING APPROACHES IS THAT THEY REQUIRE AN ENORMOUS AMOUNT OF MANUALLY CURATED TRAINING DATA IN ORDER TO PROVIDE ACCURATE TRANSLATIONS. WE PRESENT DBPAL THAT USES A NOVEL TRAINING PIPELINE TO LEARN NL2SQL INTERFACES WHICH SYNTHESIZES TRAINING DATA AND, THUS, DOES NOT RELY ON MANUALLY CURATED TRAINING DATA.

Download full text files

Export metadata

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Benjamin HättaschORCiDGND, Nadja GeislerORCiDGND, Carsten BinnigORCiDGND
URN:urn:nbn:de:hebis:30:3-576404
ISSN:1866-1238
ISSN:2700-2241
Parent Title (German):Efl insights : an elf - the Data Science Institute publication
Publisher:E-Finance Lab e.V.
Place of publication:Frankfurt am Main
Document Type:Article
Language:English
Year of Completion:2020
Year of first Publication:2020
Publishing Institution:Universitätsbibliothek Johann Christian Senckenberg
Creating Corporation:E-Finance Lab <Frankfurt, Main>
Release Date:2021/01/22
Volume:2020
Issue:2
Page Number:3
First Page:6
Last Page:8
HeBIS-PPN:477066348
Institutes:Angeschlossene und kooperierende Institutionen / E-Finance Lab e.V.
Dewey Decimal Classification:3 Sozialwissenschaften / 33 Wirtschaft / 330 Wirtschaft
Sammlungen:Universitätspublikationen
Licence (German):License LogoDeutsches Urheberrecht