- Naïve Bayes classifier (NB)
- SVM with linear kernel
- Logistic Regression (LR)
- Random Forest classifier (RF)

In order to use the classifiers above, the authors concatenated the source concept and target concept vectors, then used the corresponding prerequisite relation label as the class label to fit the models.

University of Michigan - Ann Arbor

Before feeding the data to the models, the author first took 10% positive samples and the same number of negative samples as the test set and treated the rest samples as the training set. Then fed the training data to the models below on 5-fold cross-validation:
- Binary classifiers
- Graph Convolutional Networks

What Should I Learn First: Introducing LectureBank for NLP Education and Prerequisite Chain Learning: Prerequisite chain learning models

Li, I., Fabbri, A. R., Tung, R. R., & Radev, D. R. (2019, July). What should i learn first: Introducing lecturebank for nlp education and prerequisite chain learning. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 33, pp. 6674-6681).

Paper: https://www.aaai.org/ojs/index.php/AAAI/article/view/4638

Github: https://github.com/Yale-LILY/LectureBank

What Should I Learn First: Introducing LectureBank for NLP Education and Prerequisite Chain Learning: Reference

What Should I Learn First: Introducing LectureBank for NLP Education and Prerequisite Chain Learning: Prerequisite chain learning binary classifiers

The author used the non-probabilistic Graph autoencoder(GAE) and the Variational Graph Autoencoder(VGAE) with 200 epochs, a learning rate of 0.01, two-layers(32 hidden units in the first and 16 in the second). (Kipf and Welling 2016)

Learn Before

Related