Automatic Text Scoring Using Neural Networks
This work addresses the need for cost-effective and consistent automated text scoring, offering a fully automated framework that could benefit educational assessment systems.
The paper tackles the problem of automated text scoring by introducing a neural network model that learns word representations and uses LSTM networks to achieve excellent results, eliminating the need for manually engineered features.
Automated Text Scoring (ATS) provides a cost-effective and consistent alternative to human marking. However, in order to achieve good performance, the predictive features of the system need to be manually engineered by human experts. We introduce a model that forms word representations by learning the extent to which specific words contribute to the text's score. Using Long-Short Term Memory networks to represent the meaning of texts, we demonstrate that a fully automated framework is able to achieve excellent results over similar approaches. In an attempt to make our results more interpretable, and inspired by recent advances in visualizing neural networks, we introduce a novel method for identifying the regions of the text that the model has found more discriminative.