CDGP: Automatic Cloze Distractor Generation based on Pre-trained Language Model
This addresses the challenge of efficient and effective assessment in education by automating distractor generation, representing a strong specific gain rather than a broad paradigm shift.
The paper tackled the problem of automatically generating distractors for cloze tests, which is time-consuming to do manually, and achieved a state-of-the-art result by improving the NDCG@10 score from 14.94 to 34.17 using a pre-trained language model-enhanced approach.
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.