Back to Search
Start Over
CDGP: Automatic Cloze Distractor Generation based on Pre-trained Language Model
- Source :
- chiang-etal-2022-cdgp
- Publication Year :
- 2024
-
Abstract
- 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.<br />Comment: Findings of short paper, EMNLP 2022
Details
- Database :
- arXiv
- Journal :
- chiang-etal-2022-cdgp
- Publication Type :
- Report
- Accession number :
- edsarx.2403.10326
- Document Type :
- Working Paper
- Full Text :
- https://doi.org/10.18653/v1/2022.findings-emnlp.429