Dissertation/ Thesis
Large language model based automated translation of natural language to SQL ; Büyük dil modeli tabanlı doğal dilden SQL’e otomatik çeviri
| Title: | Large language model based automated translation of natural language to SQL ; Büyük dil modeli tabanlı doğal dilden SQL’e otomatik çeviri |
|---|---|
| Authors: | Kanburoğlu, Ali Buğra |
| Contributors: | Tek, Faik Boray, Işık Üniversitesi, Lisansüstü Eğitim Enstitüsü, Bilgisayar Mühendisliği Doktora Programı, Işık University, School of Graduate Studies, Ph.D. in Computer Engineering |
| Publisher Information: | Işık Üniversitesi, Lisansüstü Eğitim Enstitüsü |
| Publication Year: | 2025 |
| Collection: | Işık Üniversitesi: DSpace Repository |
| Subject Terms: | Text-to-SQL, LLM, TUR2SQL, TURSpider, MoA, BDM, QA76.73.S67 K36 2025, SQL (Computer program language), Deep learning (Machine learning) |
| Description: | Text in English ; Abstract: Turkish and English ; Includes bibliographical references (leaves 66-75) ; xiii, 76 leaves ; The field of Text-to-SQL, which involves converting natural language into SQL queries, has seen significant advancements, but challenges remain, particularly for low-resource languages like Turkish. This thesis introduces three key contributions to address these challenges. Our first contribution is the development and open-access release of TUR2SQL, the first cross-domain Turkish Text-to-SQL dataset, which consists of 10,809 natural language sentences paired with their corresponding SQL queries. We evaluate the performance of SQLNet, a deep learning model specifically designed for this task, and one of the most successful Large Language Models (LLMs), ChatGPT, on this dataset. The results demonstrate the superior performance of ChatGPT. The second major contribution is the construction and publicly available release of TURSpider, the most extensive Turkish Text-to-SQL dataset. TURSpider is built by translating the widely used cross-domain Spider dataset from English to Turkish. This dataset includes complex queries with varying difficulty levels, facilitating the training and comparison of large language models for Turkish Text-to-SQL tasks. Our comparative analysis shows that fine-tuned Turkish LLMs achieve competitive performance, with some models surpassing OpenAI models in query accuracy. To further enhance performance, we apply the Chainof-Feedback (CoF) methodology, demonstrating its effectiveness across multiple models. Finally, we explore the Mixture-of-Agents (MoA) framework, which combines outputs from multiple models to improve the performance of open-source LLMs for Text-to-SQL tasks. By integrating MoA with the CoF technique, we propose MoAF-SQL, an approach that significantly improves performance, particularly on complex queries. Our experiments show that MoAF-SQL achieves competitive results, highlighting its potential to enhance the Text-to-SQL capabilities of open-source ... |
| Document Type: | doctoral or postdoctoral thesis |
| File Description: | application/pdf |
| Language: | English |
| Relation: | Tez; Kanburoğlu, A. B. (2025). Large language model based automated translation of natural language to SQL. İstanbul: Işık Üniversitesi Lisansüstü Eğitim Enstitüsü.; https://hdl.handle.net/11729/6412; 927714 |
| Availability: | https://hdl.handle.net/11729/6412 |
| Rights: | info:eu-repo/semantics/openAccess |
| Accession Number: | edsbas.EDA291AF |
| Database: | BASE |
| FullText | Text: Availability: 0 CustomLinks: – Url: https://hdl.handle.net/11729/6412# Name: EDS - BASE (ns324271) Category: fullText Text: View record from BASE |
|---|---|
| Header | DbId: edsbas DbLabel: BASE An: edsbas.EDA291AF RelevancyScore: 900 AccessLevel: 3 PubType: Dissertation/ Thesis PubTypeId: dissertation PreciseRelevancyScore: 899.809631347656 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Large language model based automated translation of natural language to SQL ; Büyük dil modeli tabanlı doğal dilden SQL’e otomatik çeviri – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Kanburoğlu%2C+Ali+Buğra%22">Kanburoğlu, Ali Buğra</searchLink> – Name: Author Label: Contributors Group: Au Data: Tek, Faik Boray<br />Işık Üniversitesi, Lisansüstü Eğitim Enstitüsü, Bilgisayar Mühendisliği Doktora Programı<br />Işık University, School of Graduate Studies, Ph.D. in Computer Engineering – Name: Publisher Label: Publisher Information Group: PubInfo Data: Işık Üniversitesi, Lisansüstü Eğitim Enstitüsü – Name: DatePubCY Label: Publication Year Group: Date Data: 2025 – Name: Subset Label: Collection Group: HoldingsInfo Data: Işık Üniversitesi: DSpace Repository – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Text-to-SQL%22">Text-to-SQL</searchLink><br /><searchLink fieldCode="DE" term="%22LLM%22">LLM</searchLink><br /><searchLink fieldCode="DE" term="%22TUR2SQL%22">TUR2SQL</searchLink><br /><searchLink fieldCode="DE" term="%22TURSpider%22">TURSpider</searchLink><br /><searchLink fieldCode="DE" term="%22MoA%22">MoA</searchLink><br /><searchLink fieldCode="DE" term="%22BDM%22">BDM</searchLink><br /><searchLink fieldCode="DE" term="%22QA76%2E73%2ES67+K36+2025%22">QA76.73.S67 K36 2025</searchLink><br /><searchLink fieldCode="DE" term="%22SQL+%28Computer+program+language%29%22">SQL (Computer program language)</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning+%28Machine+learning%29%22">Deep learning (Machine learning)</searchLink> – Name: Abstract Label: Description Group: Ab Data: Text in English ; Abstract: Turkish and English ; Includes bibliographical references (leaves 66-75) ; xiii, 76 leaves ; The field of Text-to-SQL, which involves converting natural language into SQL queries, has seen significant advancements, but challenges remain, particularly for low-resource languages like Turkish. This thesis introduces three key contributions to address these challenges. Our first contribution is the development and open-access release of TUR2SQL, the first cross-domain Turkish Text-to-SQL dataset, which consists of 10,809 natural language sentences paired with their corresponding SQL queries. We evaluate the performance of SQLNet, a deep learning model specifically designed for this task, and one of the most successful Large Language Models (LLMs), ChatGPT, on this dataset. The results demonstrate the superior performance of ChatGPT. The second major contribution is the construction and publicly available release of TURSpider, the most extensive Turkish Text-to-SQL dataset. TURSpider is built by translating the widely used cross-domain Spider dataset from English to Turkish. This dataset includes complex queries with varying difficulty levels, facilitating the training and comparison of large language models for Turkish Text-to-SQL tasks. Our comparative analysis shows that fine-tuned Turkish LLMs achieve competitive performance, with some models surpassing OpenAI models in query accuracy. To further enhance performance, we apply the Chainof-Feedback (CoF) methodology, demonstrating its effectiveness across multiple models. Finally, we explore the Mixture-of-Agents (MoA) framework, which combines outputs from multiple models to improve the performance of open-source LLMs for Text-to-SQL tasks. By integrating MoA with the CoF technique, we propose MoAF-SQL, an approach that significantly improves performance, particularly on complex queries. Our experiments show that MoAF-SQL achieves competitive results, highlighting its potential to enhance the Text-to-SQL capabilities of open-source ... – Name: TypeDocument Label: Document Type Group: TypDoc Data: doctoral or postdoctoral thesis – Name: Format Label: File Description Group: SrcInfo Data: application/pdf – Name: Language Label: Language Group: Lang Data: English – Name: NoteTitleSource Label: Relation Group: SrcInfo Data: Tez; Kanburoğlu, A. B. (2025). Large language model based automated translation of natural language to SQL. İstanbul: Işık Üniversitesi Lisansüstü Eğitim Enstitüsü.; https://hdl.handle.net/11729/6412; 927714 – Name: URL Label: Availability Group: URL Data: https://hdl.handle.net/11729/6412 – Name: Copyright Label: Rights Group: Cpyrght Data: info:eu-repo/semantics/openAccess – Name: AN Label: Accession Number Group: ID Data: edsbas.EDA291AF |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.EDA291AF |
| RecordInfo | BibRecord: BibEntity: Languages: – Text: English Subjects: – SubjectFull: Text-to-SQL Type: general – SubjectFull: LLM Type: general – SubjectFull: TUR2SQL Type: general – SubjectFull: TURSpider Type: general – SubjectFull: MoA Type: general – SubjectFull: BDM Type: general – SubjectFull: QA76.73.S67 K36 2025 Type: general – SubjectFull: SQL (Computer program language) Type: general – SubjectFull: Deep learning (Machine learning) Type: general Titles: – TitleFull: Large language model based automated translation of natural language to SQL ; Büyük dil modeli tabanlı doğal dilden SQL’e otomatik çeviri Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Kanburoğlu, Ali Buğra – PersonEntity: Name: NameFull: Tek, Faik Boray – PersonEntity: Name: NameFull: Işık Üniversitesi, Lisansüstü Eğitim Enstitüsü, Bilgisayar Mühendisliği Doktora Programı – PersonEntity: Name: NameFull: Işık University, School of Graduate Studies, Ph.D. in Computer Engineering IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 01 Type: published Y: 2025 Identifiers: – Type: issn-locals Value: edsbas – Type: issn-locals Value: edsbas.oa |
| ResultId | 1 |