Manually designing cloze test consumes enormous time and efforts. The major challenge lies in wrong option (distractor) selection. Having carefully-design distractors improves the effectiveness of learner ability assessment. As a result, the idea of automatically generating cloze distractor is motivated. In this paper, we investigate cloze distractor generation by exploring the employment of pre-trained language models (PLMs) as an alternative for candidate distractor generation. Experiments show that the PLM-enhanced model brings a substantial performance improvement. Our best performing model advances the state-of-the-art result from 14.94 to 34.17 (NDCG@10 score). Our code and dataset is available at https://github.com/AndyChiangSH/CDGP.
@article{arxiv.2403.10326,
title = {CDGP: Automatic Cloze Distractor Generation based on Pre-trained Language Model},
author = {Shang-Hsuan Chiang and Ssu-Cheng Wang and Yao-Chung Fan},
journal= {arXiv preprint arXiv:2403.10326},
year = {2024}
}