TUR2SQL: A Cross-Domain Turkish Dataset For Text-to-SQL

Ali Bugra Kanburoglu, F. Boray Tek

Araştırma sonucu: ???type-name???Konferans katkısıbilirkişi

Özet

The field of converting natural language into corresponding SQL queries using deep learning techniques has attracted significant attention in recent years. While existing Text-to-SQL datasets primarily focus on English and other languages such as Chinese, there is a lack of resources for the Turkish language. In this study, we introduce the first publicly available cross-domain Turkish Text-to-SQL dataset, named TUR2SQL. This dataset consists of 10,809 pairs of natural language statements and their corresponding SQL queries. We conducted experiments using SQLNet and ChatGPT on the TUR2SQL dataset. The experimental results show that SQLNet has limited performance and ChatGPT has superior performance on the dataset. We believe that TUR2SQL provides a foundation for further exploration and advancements in Turkish language-based Text-to-SQL research.

Orijinal dilİngilizce
Ana bilgisayar yayını başlığıUBMK 2023 - Proceedings
Ana bilgisayar yayını alt yazısı8th International Conference on Computer Science and Engineering
YayınlayanInstitute of Electrical and Electronics Engineers Inc.
Sayfalar206-211
Sayfa sayısı6
ISBN (Elektronik)9798350340815
DOI'lar
Yayın durumuYayınlandı - 2023
Etkinlik8th International Conference on Computer Science and Engineering, UBMK 2023 - Burdur, Turkey
Süre: 13 Eyl 202315 Eyl 2023

Yayın serisi

AdıUBMK 2023 - Proceedings: 8th International Conference on Computer Science and Engineering

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???8th International Conference on Computer Science and Engineering, UBMK 2023
Ülke/BölgeTurkey
ŞehirBurdur
Periyot13/09/2315/09/23

Bibliyografik not

Publisher Copyright:
© 2023 IEEE.

Parmak izi

TUR2SQL: A Cross-Domain Turkish Dataset For Text-to-SQL' araştırma başlıklarına git. Birlikte benzersiz bir parmak izi oluştururlar.

Alıntı Yap