SavedAdd your journal

Journals / Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi / 2022 / Cilt: 11 - Sayı: 4

A study on text-to-SQL query prediction with natural language processing methods

Doğal dil işleme yöntemleriyle metinden SQL sorgusu tahmini üzerine bir çalışma

Asım Sinan YÜKSEL
Muhammed Abdulhamid KARABIYIK
Pages
846–855
Publication Date
2022-10-21
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

In the overall system evaluation with multilingual support, the success rate has reached 69.4%.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In computer science, permanent information is kept in databases in a systematic way.
📊
Key Findings & Data:Multi-language support, which is one of the main subjects of natural language processing, is integrated into the application.
💡
Conclusion & Impact:In the overall system evaluation with multilingual support, the success rate has reached 69.4%.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Doğal dil işleme · Yapay zekâ · Metinden SQL dönüşümü

Abstract

In computer science, permanent information is kept in databases in a systematic way. In order to access the information in the databases, it is necessary to have certain technical knowledge. In our study, SQL query estimation was made from natural language queries. In this way, it is aimed to make queries on databases without any technical knowledge. In our study, natural language processing techniques were used. Multi-language support, which is one of the main subjects of natural language processing, is integrated into the application. The model applied for natural language SQL prediction is trained with the spider dataset using the LSTM network. In the SQL query estimations, it has reached 75% success rate. In the overall system evaluation with multilingual support, the success rate has reached 69.4%.

Özet

Bilgisayar bilimlerinde, kalıcı bilgiler sistematik bir şekilde veri tabanlarında tutulmaktadır. Veri tabanlarındaki bilgilere ulaşılabilmesi için belirli teknik birikimlere sahip olunması gerekmektedir. Çalışmamızda, doğal dille yapılmış sorgulardan SQL sorgusu tahmini yapılmıştır. Bu sayede teknik bir bilgi birikimi olmadan veri tabanları üzerinde sorgulamalar yapılabilmesi hedeflenmektedir. Çalışmamızda doğal dil işleme tekniklerinden faydalanmıştır. Doğal dil işlemenin ana konularından biri olan çoklu dil desteği, uygulamaya entegre edilmiştir. Doğal dilden SQL tahmini için uygulanan model, LSTM ağı kullanılarak spider veri setiyle eğitilmiştir. Yapılan SQL sorgusu tahminlerinde, %75 başarı oranına ulaşmıştır. Çoklu dil desteğiyle yapılan genel sistem değerlendirmesinde, başarı oranı %69.4’ e ulaşmıştır.

🔖

Cite This Article

YÜKSEL, A. S., KARABIYIK, M. A. (2022). A study on text-to-SQL query prediction with natural language processing methods. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, Cilt: 11 - Sayı: 4, 846–855. https://ajindex.com/articles/584377

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (15)

  1. E. Adalı, Doğal dil işleme. Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi, 5 (2), 2012.
  2. R. C. Moore, Practical natural-language processing by computer. SRI Internatıonal Menlo Park CA Artıfıcıal Intellıgence Center, 1981.
  3. Y. Yu, X. Si, C. Hu, and J. Zhang, A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures, Neural Computation, 31 (7), 1235–1270, 2019. https://doi.org/10.1162/neco_a_0 1199. T. Yu et al., Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task. arXiv preprint arXiv:1809.08887, 2018.
  4. O. Rubin and J. Berant, SmBoP: Semi-autoregressive Bottom-up Semantic Parsingi arXiv preprint arXiv:2010.12412, 2020. Spider: Yale Semantic Parsing and Text-to-SQL Challenge. https://yale-lily.github.io/spider (acces sed May 11, 2022).
  5. J. F. Allen, Natural Language Processing, Encyclopedia of Computer Science. John Wiley and Sons Ltd., Londra, 2003.
  6. B. John and Z. Michael, Natural Language Generation. Oxford University Press, Oxford, 2012.
  7. T. Alan M, Computing machinery and intelligence, in Parsing the turing test. Springer, Dordrecht, 2009. M. A. Chéragui, Theoretical overview of machine translation. International Conference on Web and Information Technologies, pp. 160-169,
  8. Sidi Bel-Abbes, Algeria, 2012.
  9. D. H. Klatt, Review of the ARPA speech understanding Project. The Journal of the Acoustical Society of America, 62 (6), 1345-1366, 1977.
  10. M. Benzeghiba et al., Automatic speech recognition and speech variability: A review. Speech communication, 49(10-11), 763-786, 2007. https://doi.org/10.1016/j.specom.2007.02.006.
  11. K. Frank, Gradience in grammar: Experimental and computational aspects of degrees of grammaticality. Ph.D. Thesis, Rutgers University, New Jersey, USA, 2000.
  12. C. David, Lexical acquisition in the core language engine. Fourth Conference of the European Chapter of the Association for Computational Linguistics, 1989.
  13. J. Karen Sparc, Natural language processing: a historical review. Linguistica Computazionale, Springer, Dordrecht, 1994.
  14. K. Nigam, M. Andrew, T. Sebastian, and M. Tom, Learning to classify text from labeled and unlabeled documents. Proceedings of the Fifteenth National/Tenth Conference on Artificial Intelli gence/Innovative Applications of Artificial Intelligence, pp. 792-799, 1998.
  15. W. Casey, H. Ben, C. Grace Y, and E. Gerard, Using the web for language ındependent spellchecking and autocorrection. Conference on Empirical Methods in Natural Lan