LGJan 23, 2020
Applying Recent Innovations from NLP to MOOC Student Course Trajectory ModelingClarence Chen, Zachary Pardos
This paper presents several strategies that can improve neural network-based predictive methods for MOOC student course trajectory modeling, applying multiple ideas previously applied to tackle NLP (Natural Language Processing) tasks. In particular, this paper investigates LSTM networks enhanced with two forms of regularization, along with the more recently introduced Transformer architecture.