prikaz prve stranice dokumenta Stvaranje naredbi jezika SQL na osnovi opisa zadanog prirodnim jezikom
No public access
master's thesis
Stvaranje naredbi jezika SQL na osnovi opisa zadanog prirodnim jezikom
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. urn:nbn:hr:168:741592
Primorac, Juraj
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Primorac, J. (2019). Stvaranje naredbi jezika SQL na osnovi opisa zadanog prirodnim jezikom (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:741592

Primorac, Juraj. "Stvaranje naredbi jezika SQL na osnovi opisa zadanog prirodnim jezikom." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:741592

Primorac, Juraj. "Stvaranje naredbi jezika SQL na osnovi opisa zadanog prirodnim jezikom." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:741592

Primorac, J. (2019). 'Stvaranje naredbi jezika SQL na osnovi opisa zadanog prirodnim jezikom', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 26 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:741592

Primorac J. Stvaranje naredbi jezika SQL na osnovi opisa zadanog prirodnim jezikom [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2019 [cited 2024 November 26] Available at: https://urn.nsk.hr/urn:nbn:hr:168:741592

J. Primorac, "Stvaranje naredbi jezika SQL na osnovi opisa zadanog prirodnim jezikom", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:168:741592

Metadata
TitleStvaranje naredbi jezika SQL na osnovi opisa zadanog prirodnim jezikom
Title (english)Generating SQL Language Instructions Based on the Natural Language Description
AuthorJuraj Primorac
MentorMarin Šilić (mentor)
Committee memberMarin Šilić (predsjednik povjerenstva)
Committee memberSiniša Srbljić (član povjerenstva)
Committee memberGoran Delač (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2019-07-08, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Generiranje SQL upita iz opisa na prirodnom jeziku je otvoreni problem i privlači značajan interes. Zanimanje za sučelja prirodnog jezika prema bazi podataka se pobudilo zbog napretka u dubokom učenju i razvoja prikladnih setova za učenje modela. Zbog nedavnog uspjeha dubokog učenja u prevođenju prirodnog jezika u SQL cilj ovoga rada je istražiti područje dubokog učenja u kontekstu obrade prirodnog jezika, kao i prirodna jezična sučelja za bazu podataka općenito. U skladu s tim ciljem, odabrani modeli se obučavaju na skupu podataka koji uključuju SQL upite i upite na prirodnom jeziku koji se odnose na geografiju SAD-a. Opisana je struktura, obuka i implementacija modela. Rezultati se mjere i uspoređuju s drugim pristupima. Ključne riječi: SQL, obrada prirodnog jezika, baza podataka, neuronska mreža, strojno učenje, duboko učenje, prevođenje sekvence u sekvencu, PyTorch, AllenNLP, enkoder, dekoder
Abstract (english)
SQL query generation based on natural language description is a long-standing open problem and has been attracting considerable interest recently. There is a renewed interest in natural language interfaces to databases due to the advance in deep learning and the release of large-scale annotated data. In the fashion of recent success of deep neural approaches in natural language to SQL processing, aim of this thesis is to explore the field of Deep Learning in the context of Natural Language Processing, as well as Natural Language Interfaces to Database in general. In accordance with that goal, a selected Sequence to SQL model is trained on a dataset to generate SQL queries from natural language queries about USA geography. Structure, training and deploying of the model are described. Results are measured and compared to other approaches.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:741592
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2020-01-07 21:34:43