Natural Language to SQL Queries: A Review

Baig, Mirza Shahzaib; Imran, Azhar; Yasin, Amanullah; Butt, Abdul Haleem; Khan, Muhammad Imran

doi:10.33411/ijist/2022040111

Cited by 6 publications

(3 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The capabilities of LLMs, such as Natural Language to SQL (NL2SQL) [9], enable the conversion of user queries or requirements expressed in natural language into database query language (SQL), meeting the needs of management and providing timely responses for hospital management. The application of this technology not only enhances the e ciency of data processing but also reduces the manual handling workload, allowing hospital informatization efforts to focus more on in-depth analysis and interpretation of data results [10].…”

Section: Introductionmentioning

confidence: 99%

Exploring the Prospects of LLMs in Hospital Management: A Perspective on Medical data inquiry

Li,

Zhang,

Zhang

et al. 2024

Preprint

View full text Add to dashboard Cite

Background In light of the rapid expansion of hospital operations and the increasing digitization of medical data, there is a pressing need for efficient and intelligent methods to process and analyze large-scale medical data. Methods To tackle these challenges, the study integrates the QLoRA algorithm with ChatGLM2-6b and Llama2-6b models. These models undergo fine-tuning on a local SQL dataset, with a specific emphasis on optimizing performance, especially for simpler queries. Subsequently, we employ Prompt-Engineering with ChatGPT-3.5, enabling us to effectively leverage its capabilities and tailor its outputs to execute SQL queries. Results The comprehensive big data platform illustrates the evolution of inpatient operations, encompassing diverse information such as patient diagnoses, surgeries, medications, and examinations across various healthcare domains. The integration of the QLoRA algorithm with ChatGLM2-6b and Llama2-6b models, combined with fine-tuning on a local SQL dataset, enhances the model's performance on simple and moderately difficult SQL queries. Notably, after minimal training, the ChatGPT3.5 model closely approximates the results of human engineers in terms of SQL query performance, achieving an accuracy of approximately 90%. Conclusion The strategic utilization of Large Language Models (LLMs) and Natural Language to SQL (NL2SQL) generation enhances the efficiency of medical data analysis. This approach provides a robust foundation for decision-making in hospital management amid the evolving landscape of healthcare operations and data queries.

show abstract

Section: Introductionmentioning

confidence: 99%

Exploring the Prospects of LLMs in Hospital Management: A Perspective on Medical data inquiry

Li,

Zhang,

Zhang

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…These parts predict the operator symbols, select column names, and Where clauses of the target statement, ultimately concatenating these components to form a complete query statement. Building upon the SEQ2SQL model, the subsequent SQLNet model introduced the ideas of set-to-sequence and column attention, leading to improved accuracy in SQL generation [6].…”

Section: Introductionmentioning

confidence: 99%

Research on large model table question answering method based on thought of chain and vector matching filtering

Tang,

Wang,

et al. 2024

Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024)

View full text Add to dashboard Cite

Implementing table-based question answering can fully leverage the rich information in tabular data, and the development of large language models has provided strong natural language processing and understanding capabilities. Current research on table-based question answering with large language models mainly focuses on how to improve text-to-SQL abilities and the development of table pre-training models, lacking in studies on feasible technical approaches for applying general large language models to engineering applications involving large-scale database table question answering. In response, combining techniques such as prompt learning and chain of thought，this paper constructs a database question answering chain of thought based on large language model, proposes a table filtering scheme based on vectorized matching of table structural information, specifically addressing poor table filtering effects, and constructs a database optimization chain of thought in the context of de-identification scenarios. Experimental verification shows that after adopting the chain of thought construction and vector matching filtering scheme, the database question answering capability of the large model has been effectively improved.

show abstract

“…, A variety of learning methods have been used to improve the performance of DA algorithm, but no one worked on optimal bidding price. The main problem occurs when multiple bid prices come in the auction algorithm, and we need to achieve equilibrium prices during the algorithm's execution [5]. The resource allocation process depends upon the bidding price.…”

Section: Introductionmentioning

confidence: 99%

Double Auction used Artificial Neural Network in Cloud Computing

Abbas

Iqbal

2022

IJIST

View full text Add to dashboard Cite

Double auction (DA) algorithm is widely used for trading systems in cloud computing. Distinct buyers request different attributes for virtual machines. On the other hand, different sellers offer several types of virtual machines according to their correspondence bids. In DA, getting multiple equilibrium prices from distinct cloud providers is a difficult task, and one of the major problems is bidding prices for virtual machines, so we cannot make decisions with inconsistent data. To solve this problem, we need to find the best machine learning algorithm that anticipates the bid cost for virtual machines. Analyzing the performance of DA algorithm with machine learning algorithms is to predict the bidding price for both buyers and sellers. Therefore, we have implemented several machine learning algorithms and observed their performance on the bases of accuracy, such as linear regression (83%), decision tree regressor (77%), random forest (82%), gradient boosting (81%), and support vector regressor (90%). In the end, we observed that the Artificial Neural Network (ANN) provided an astonishing result. ANN has provided 97% accuracy in predicting bidding prices in DA compared to all other learning algorithms. It reduced the wastage of resources (VMs attributes) and soared both users' profits (buyers & sellers). Different types of models were analyzed on the bases of individual parameters such as accuracy. In the end, we found that ANN is effective and valuable for bidding prices for both users.

show abstract

Natural Language to SQL Queries: A Review

Cited by 6 publications

References 39 publications

Exploring the Prospects of LLMs in Hospital Management: A Perspective on Medical data inquiry

Exploring the Prospects of LLMs in Hospital Management: A Perspective on Medical data inquiry

Research on large model table question answering method based on thought of chain and vector matching filtering

Double Auction used Artificial Neural Network in Cloud Computing

Contact Info

Product

Resources

About