Few-shot Question Generation for Personalized Feedback in Intelligent Tutoring Systems

TL;DR

This paper presents a novel few-shot neural question generation approach for personalized feedback in Intelligent Tutoring Systems, significantly improving student learning outcomes by providing targeted, natural language questions that address specific answer components.

Contribution

It introduces a combined cause-effect analysis and Transformer-based NLP method for personalized, component-specific question generation in ITS, outperforming existing baselines.

Findings

Achieved 45% and 23% improvements in student learning gains over baselines.

Demonstrated effectiveness of personalized questions in guiding students to correct answers.

Showed potential for enhancing Generative Question Answering systems.

Abstract

Existing work on generating hints in Intelligent Tutoring Systems (ITS) focuses mostly on manual and non-personalized feedback. In this work, we explore automatically generated questions as personalized feedback in an ITS. Our personalized feedback can pinpoint correct and incorrect or missing phrases in student answers as well as guide them towards correct answer by asking a question in natural language. Our approach combines cause-effect analysis to break down student answers using text similarity-based NLP Transformer models to identify correct and incorrect or missing parts. We train a few-shot Neural Question Generation and Question Re-ranking models to show questions addressing components missing in the student answers which steers students towards the correct answer. Our model vastly outperforms both simple and strong baselines in terms of student learning gains by 45% and 23% respectively when tested in a real dialogue-based ITS. Finally, we show that our personalized corrective feedback system has the potential to improve Generative Question Answering systems.