Deep Factorization Machines for Knowledge Tracing
This work addresses knowledge tracing for language learners, but it is incremental as it adapts an existing method to a specific dataset without surpassing the best performance.
The paper tackled the 2018 Duolingo Shared Task on Second Language Acquisition Modeling by applying deep factorization machines to model pairwise relationships between entities like users and skills, achieving an AUC of 0.815, which improved upon a logistic regression baseline (AUC 0.774) but fell short of the top model (AUC 0.861).
This paper introduces our solution to the 2018 Duolingo Shared Task on Second Language Acquisition Modeling (SLAM). We used deep factorization machines, a wide and deep learning model of pairwise relationships between users, items, skills, and other entities considered. Our solution (AUC 0.815) hopefully managed to beat the logistic regression baseline (AUC 0.774) but not the top performing model (AUC 0.861) and reveals interesting strategies to build upon item response theory models.