The Effectiveness of a Dynamic Loss Function in Neural Network Based Automated Essay Scoring
This work addresses a specific issue in automated essay scoring for educational applications, but it is incremental as it builds on existing neural network methods.
The paper tackled the problem of underfitting in regression-based neural networks for automated essay scoring by introducing a dynamic loss function that encourages correct distribution predictions, achieving a Quadratic Weighted Kappa score of 0.752 on a standard dataset.
Neural networks and in particular the attention mechanism have brought significant advances to the field of Automated Essay Scoring. Many of these systems use a regression-based model which may be prone to underfitting when the model only predicts the mean of the training data. In this paper, we present a dynamic loss function that creates an incentive for the model to predict with the correct distribution, as well as predicting the correct values. Our loss function achieves this goal without sacrificing any performance achieving a Quadratic Weighted Kappa score of 0.752 on the Automated Student Assessment Prize Automated Essay Scoring dataset.