Translating Natural Language Queries to SQL Using the T5 Model

被引：0

作者：

Wong, Albert ^{[1
]}

Pham, Lien ^{[1
]}

Lee, Young ^{[2
]}

Chan, Shek ^{[1
]}

Sadaya, Razel ^{[1
]}

Khmelevsky, Youry ^{[3
]}

Clement, Mathias ^{[3
]}

Cheng, Florence Wing Yau ^{[1
]}

Mahony, Joe ^{[4
]}

Ferri, Michael ^{[4
]}

机构：

[1] Langara Coll, Math & Stat, Vancouver, BC, Canada

[2] Okanagan Coll, Math & Stat, Kelowna, BC, Canada

[3] Okanagan Coll, Comp Sci, Kelowna, BC, Canada

[4] Harris SmartWorks, Res & Dev, Ottawa, ON, Canada

来源：

18TH ANNUAL IEEE INTERNATIONAL SYSTEMS CONFERENCE, SYSCON 2024 | 2024年

基金：

加拿大自然科学与工程研究理事会;

关键词：

Natural Language Processing; Data Query System; Text-to-SQL; Speech-to-SQL; Deep Learning; Machine Learning; T5; Model; Human-Machine-Systems; Energy Systems;

D O I：

10.1109/SysCon61195.2024.10553509

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

This paper presents the development process of a natural language to SQL model using the T5 model as the basis. The models, developed in August 2022 for an online transaction processing system and a data warehouse, have a 73% and 84% exact match accuracy respectively. These models, in conjunction with other work completed in the research project, were implemented for several companies and used successfully on a daily basis. The approach used in the model development could be implemented in a similar fashion for other database environments and with a more powerful pre-trained language model.

引用

页数：7

共 50 条

[21] Comparative analysis of paraphrasing performance of ChatGPT, GPT-3, and T5 language models using a new ChatGPT generated dataset: ParaGPT
Pehlivanoglu, Meltem Kurt
Gobosho, Robera Tadesse
Syakura, Muhammad Abdan
Shanmuganathan, Vimal
de-la-Fuente-Valentin, Luis
EXPERT SYSTEMS, 2024, 41 (11)
[22] Locating SQL Injection Vulnerabilities in Java']Java Byte Code using Natural Language Techniques
Jackson, Kevin A.
Bennett, Brian T.
IEEE SOUTHEASTCON 2018, 2018,
[23] Chatbot Interaction with Artificial Intelligence: human data augmentation with T5 and language transformer ensemble for text classification
Jordan J. Bird
Anikó Ekárt
Diego R. Faria
Journal of Ambient Intelligence and Humanized Computing, 2023, 14 : 3129 - 3144
[24] Searching for musical features using natural language queries: the C@merata evaluations at MediaEval
Richard Sutcliffe
Eduard Hovy
Tom Collins
Stephen Wan
Tim Crawford
Deane L. Root
Language Resources and Evaluation, 2019, 53 : 87 - 140
[25] NL2API: A Framework for Bootstrapping Service Recommendation using Natural Language Queries
Lin, Chen
Kalia, Anup K.
Xiao, Jin
Vukovic, Maja
Anerousis, Nikos
2018 IEEE INTERNATIONAL CONFERENCE ON WEB SERVICES (IEEE ICWS 2018), 2018, : 235 - 242
[26] Intelligent Processing of Natural Language Search Queries Using Semantic Mapping for User Intention Extracting
Chernyshov, Artyom
Balandina, Anita
Klimov, Valentin
BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES 2018, 2019, 848 : 56 - 61
[27] Searching for musical features using natural language queries: the C@merata evaluations at MediaEval
Sutcliffe, Richard
Hovy, Eduard
Collins, Tom
Wan, Stephen
Crawford, Tim
Root, Deane L.
LANGUAGE RESOURCES AND EVALUATION, 2019, 53 (01) : 87 - 140
[28] Chatbot Interaction with Artificial Intelligence: human data augmentation with T5 and language transformer ensemble for text classification
Bird, Jordan J.
Ekart, Aniko
Faria, Diego R.
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING, 2021, 14 (4) : 3129 - 3144
[29] Explicable knowledge graph (X-KG): generating knowledge graphs for explainable artificial intelligence and querying them by translating natural language queries to SPARQL
Shaikh N.
Chauhan T.
Patil J.
Sonawane S.
International Journal of Information Technology, 2024, 16 (3) : 1605 - 1615
[30] A Phishing-Attack-Detection Model Using Natural Language Processing and Deep Learning
Benavides-Astudillo, Eduardo
Fuertes, Walter
Sanchez-Gordon, Sandra
Nunez-Agurto, Daniel
Rodriguez-Galan, German
APPLIED SCIENCES-BASEL, 2023, 13 (09):

← 1 2 3 4 5 →