Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

An Automated SQL Query Grading System Using An Attention-Based Convolutional Neural Network

Donald R. Schwartz, Pablo Rivas

TL;DR

This paper describes a novel approach to automating the process of grading SQL queries that employs a unique convolutional neural network architecture that employs a parameter-sharing approach for different machine learning tasks that enables the architecture to induce different knowledge representations of the data to increase its potential for understanding SQL statements.

Abstract

Grading SQL queries can be a time-consuming, tedious and challenging task, especially as the number of student submissions increases. Several systems have been introduced in an attempt to mitigate these challenges, but those systems have their own limitations. This paper describes our novel approach to automating the process of grading SQL queries. Unlike previous approaches, we employ a unique convolutional neural network architecture that employs a parameter-sharing approach for different machine learning tasks that enables the architecture to induce different knowledge representations of the data to increase its potential for understanding SQL statements.

An Automated SQL Query Grading System Using An Attention-Based Convolutional Neural Network

TL;DR

This paper describes a novel approach to automating the process of grading SQL queries that employs a unique convolutional neural network architecture that employs a parameter-sharing approach for different machine learning tasks that enables the architecture to induce different knowledge representations of the data to increase its potential for understanding SQL statements.

Abstract

Grading SQL queries can be a time-consuming, tedious and challenging task, especially as the number of student submissions increases. Several systems have been introduced in an attempt to mitigate these challenges, but those systems have their own limitations. This paper describes our novel approach to automating the process of grading SQL queries. Unlike previous approaches, we employ a unique convolutional neural network architecture that employs a parameter-sharing approach for different machine learning tasks that enables the architecture to induce different knowledge representations of the data to increase its potential for understanding SQL statements.
Paper Structure (14 sections, 8 figures)

This paper contains 14 sections, 8 figures.

Table of Contents

  1. Introduction
  2. Background
  3. Description of the Database Components
  4. Description of the Machine Learning System
  5. Embedding Layer
  6. Convolutional Self-Attention Layer
  7. Dropout Layer
  8. Batch normalization Layers
  9. Bottleneck Layer
  10. Outputs C, R, and G
  11. Experiments, Evaluation, and Results
  12. Jointly trained model cross-validated performance.
  13. LOO cross-validation on all models.
  14. Conclusions and Future Work

Figures (8)

  • Figure 1: Proposed neural architecture for SQL Statement grading based on self-attention, CNNs, and parameter sharing.
  • Figure 2: ROC curves and corresponding AUC across the 10 different folds. The average AUC is 0.64. In all folds, the model performs better than random chance.
  • Figure 3: Confusion matrix for the model that predicts correctness.
  • Figure 4: ROC and AUC for the model that predicts correctness.
  • Figure 5: Precision-Recall curves and average precision scores per remark.
  • ...and 3 more figures