Summary of Student Answer Forecasting: Transformer-driven Answer Choice Prediction For Language Learning, by Elena Grazia Gado et al.
Student Answer Forecasting: Transformer-Driven Answer Choice Prediction for Language Learning
by Elena Grazia Gado, Tommaso Martorella, Luca Zunino, Paola Mejia-Domenzain, Vinitra Swamy, Jibril Frej, Tanja Käser
First submitted to arxiv on: 30 May 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Computers and Society (cs.CY); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel approach to Intelligent Tutoring Systems (ITS) is proposed, focusing on predicting students’ specific answer choices rather than just their correctness. The MCQStudentBert model leverages Large Language Models (LLMs) to integrate contextual understanding of students’ answering history and question text. This enables practitioners to extend the model to new answer choices or remove existing ones without retraining. Comparisons are made between MLP, LSTM, BERT, and Mistral 7B architectures for generating embeddings from students’ past interactions, which are then incorporated into a finetuned BERT’s answer-forecasting mechanism. The pipeline is applied to a language learning MCQ dataset gathered from an ITS with over 10,000 students, exploring the predictive accuracy of MCQStudentBert in comparison to correct answer prediction and traditional mastery-learning feature-based approaches. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Intelligent Tutoring Systems help personalize learning by providing customized instruction based on student answers. However, most research focuses on just getting the answer right, not understanding how students think. This paper introduces a new way to predict what students will choose for their answers, which can be used in many different situations. We compare four different approaches (MLP, LSTM, BERT, and Mistral 7B) to see which one works best for generating these predictions. Our results show that this approach can accurately predict student choices and provide better support. |
Keywords
» Artificial intelligence » Bert » Lstm
