Automatic story and item generation for reading comprehension assessments with transformers

Authors : Okan BULUT, Seyma Nur YİLDİRİMERBASLİ

Pages : 72-87

Doi:10.21449/ijate.1124382

View : 19 | Download : 25

Publication Date : 2022-11-29

Article Type : Research Paper

Abstract :Reading comprehension is one of the essential skills for students as they make a transition from learning to read to reading to learn. Over the last decade, the increased use of digital learning materials for promoting literacy skills insert ignore into journalissuearticles values(e.g., oral fluency and reading comprehension); in K-12 classrooms has been a boon for teachers. However, instant access to reading materials, as well as relevant assessment tools for evaluating students’ comprehension skills, remains to be a problem. Teachers must spend many hours looking for suitable materials for their students because high-quality reading materials and assessments are primarily available through commercial literacy programs and websites. This study proposes a promising solution to this problem by employing an artificial intelligence insert ignore into journalissuearticles values(AI); approach. We demonstrate how to use advanced language models insert ignore into journalissuearticles values(e.g., OpenAI’s GPT-2 and Google’s T5); to automatically generate reading passages and items. Our preliminary findings suggest that with additional training and fine-tuning, open-source language models could be used to support the instruction and assessment of reading comprehension skills in the classroom. For both automatic story and item generation, the language models performed reasonably; however, the outcomes of these language models still require a human evaluation and further adjustments before sharing them with students. Practical implications of the findings and future research directions are discussed.
Keywords : Reading comprehension, Natural language processing, Automatic item generation, Language modeling, Text generation