Reproduce “Student Answer Forecasting: Transformer-Driven Answer Choice Prediction for Language Learning” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Elena Grazia Gado, Tommaso Martorella, Luca Zunino, Paola Mejia-Domenzain, Vinitra Swamy, Jibril Frej, Tanja Käser
The paper presents a model that predicts which multiple-choice answer a student is likely to select by combining question-and-answer text with an embedding of the student's past interactions. On held-out student-answer data from one German-language tutoring system, the history-aware model reaches 0.579 MCC, versus 0.518 without student history. The test uses questions seen before, but not for that student.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.