Contextual Embeddings and Graph Convolutional Networks for Concept Prerequisite Learning

Concept prerequisite learning (CPL) plays a crucial role in education. The objective of CPL is to predict prerequisite relations between different concepts. In this paper, we present a new approach for CPL using Sentence Transformers and Relational Graph Convolutional Networks (R-GCNs). This approach creates concept embeddings from single-sentence definitions extracted from Wikipedia using a Sentence Transformer. These embeddings are then used as an input feature matrix for the R-GCN, in addition to a graph structure that distinguishes prerequisites and non-prerequisites as distinct link types. Furthermore, the R-GCN is optimized simultaneously on CPL and concept domain classification to enhance prerequisite prediction generalization for unseen domains. Extensive experiments on the AL-CPL dataset show the effectiveness of our approach for the in-domain and cross-domain settings, as it outperforms the State-Of-The-Art (SOTA) methods on this dataset. Finally, we introduce a novel data split algorithm for this task to address a methodological issue found in previous studies. The new data split algorithm makes CPL more challenging to solve, but also more realistic as it excludes simple inferences by transitivity.