The Internet has rich and rapidly increasing sources of high quality educational content. Inferring prerequisite relations between educational concepts is required for modern large-scale online educational technology applications such as personalized recommendations and automatic curriculum creation. We present PREREQ, a new supervised learning method for inferring concept prerequisite relations. PREREQ is designed using latent representations of concepts obtained from the Pairwise Latent Dirichlet Allocation model, and a neural network based on the Siamese network architecture. PREREQ can learn unknown concept prerequisites from course prerequisites and labeled concept prerequisite data. It outperforms state-of-the-art approaches on benchmark datasets and can effectively learn from very less training data. PREREQ can also use unlabeled video playlists, a steadily growing source of training data, to learn concept prerequisites, thus obviating the need for manual annotation of course prerequisites.
Cite
@article{arxiv.1811.12640,
title = {Inferring Concept Prerequisite Relations from Online Educational Resources},
author = {Sudeshna Roy and Meghana Madhyastha and Sheril Lawrence and Vaibhav Rajan},
journal= {arXiv preprint arXiv:1811.12640},
year = {2019}
}
Comments
Accepted at the AAAI Conference on Innovative Applications of Artificial Intelligence (IAAI-19)