Enhancing Diversity in Difficulty-Controllable Question Generation for Reading Comprehension via Extended T5

Authors

  • Teruyoshi GOTO The University of Electro-Communications Author
  • Yuto TOMIKAWA The University of Electro-Communications Author
  • Masaki UTO The University of Electro-Communications Author

DOI:

https://doi.org/10.58459/icce.2024.4813

Abstract

Recently, automatic generation of reading comprehension questions with controllable difficulty levels has attracted growing interest for educational purposes. The latest method for difficulty-controllable question generation employs a two-stage mechanism utilizing two independent large language models. Specifically, given a reading passage and a difficulty level as inputs, it first produces a reference answer using BERT and then generates a corresponding question using GPT-2. However, this two-stage approach has the limitation that the questions generated depend strongly on the reference answers produced beforehand, restricting the diversity of questions. To overcome this limitation, we propose an end-to-end method that enables the simultaneous generation of questions and reference answers by extending T5, a large language model with an encoder mechanism equivalent to BERT and a decoder mechanism equivalent to GPT-2. In our method, T5 is extended to generate answers from its encoder and questions from its decoder, with the encoder's output vector passed to the decoder. Experiments using a benchmark dataset demonstrate that our method significantly improves the diversity of both questions and answers compared with the conventional method while maintaining difficulty controllability.

Downloads

Download data is not yet available.

Downloads

Published

2024-11-25

How to Cite

Enhancing Diversity in Difficulty-Controllable Question Generation for Reading Comprehension via Extended T5. (2024). International Conference on Computers in Education. https://doi.org/10.58459/icce.2024.4813