[1R5-OS-10b] AI諸技術の発展に基づく学びのモデルの高度化と展望

[1R5-OS-10b-04] Difficulty-Controllable Question Generation of Reading Comprehension using Deep Neural Networks and Item Response Theory

〇Suzuki Ayaka¹, Uto Masaki¹ (1. The University of Electro-Communications)

Keywords:Item Response Theory, Deep learning, Question Generation

Question generation (QG) for reading comprehension, a technology for automatically generating questions related to given reading passages, has been used for educational purposes. Recently, QG methods based on deep neural networks have succeeded in generating fluent questions that are pertinent to given reading passages. However, conventional methods focus only on generating questions and cannot generate answers to them. Furthermore, they ignore the relation between question difficulty and learner proficiency, making it hard to determine an appropriate difficulty for each learner. To resolve these problems, we propose a new method for generating question–answer pairs that considers their difficulty, estimated using item response theory. The proposed difficulty controllable generation is realized by extending two pre-trained transformer models, namely, BERT and GPT-2. Experimental results show that our method can generate fluent question-answer pairs with arbitrary difficult.