Papers by Yao-Chung Fan
CDGP: Automatic Cloze Distractor Generation based on Pre-trained Language Model (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to generate cloze distractors with carefully-designed distractors are limited due to wrong option selection. |
| Approach: | They propose to employ pre-trained language models as an alternative to cloze distractor generation by using pre-designed distractors. |
| Outcome: | The proposed model improves the state-of-the-art cloze test score from 14.94 to 34.17 (NDCG@10) The proposed framework improves clozing distractors by incorporating pre-trained language models. |
A BERT-based Distractor Generation Scheme with Multi-tasking and Negative Answer Training Strategies. (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Existing distractor generation methods are far from practical, and there are still room for improvement. |
| Approach: | They propose a distractor generation scheme with multi-tasking and negative answer training strategies for generating multiple distractors. |
| Outcome: | The proposed scheme improves the state-of-the-art results from 28.65 to 39.81 (BLEU 1 score) and generates multiple distractors shows strong distracting power for multiple choice questions. |
A Recurrent BERT-based Model for Question Generation (D19-58)
Copied to clipboard
| Challenge: | Existing QG models rely on recurrent neural networks (RNNs) but the inherent sequential nature of the RNN models suffers from the problem of handling long sequences. |
| Approach: | They propose to employ a pre-trained BERT language model to tackle question generation tasks. |
| Outcome: | The proposed model outperforms the existing models on the question-answering dataset SQuAD and advances the BLEU 4 score from 16.85 to 22.17. |
Enhancing Distractor Generation for Multiple-Choice Questions with Retrieval Augmented Pretraining and Knowledge Graph Integration (2024.findings-acl)
Copied to clipboard
Han Cheng Yu, Yu An Shih, Kin Man Law, KaiYu Hsieh, Yu Chen Cheng, Hsin Chih Ho, Zih An Lin, Wen-Chuan Hsu, Yao-Chung Fan
| Challenge: | Existing LMs undergo task-agnostic pertaining, but task-specific pretraining has gained prominence. |
| Approach: | They propose retrieval augmented pretraining and task-specific pretraining for DG . they propose to refine language model pretraining to align it more closely with downstream task . |
| Outcome: | The proposed method improves the performance of multiple-choice questions by integrating knowledge graphs and language models. |
Distractor Generation based on Text2Text Language Models with Pseudo Kullback-Leibler Divergence Regulation (2023.findings-acl)
Copied to clipboard
Hui-Juan Wang, Kai-Yu Hsieh, Han-Cheng Yu, Jui-Ching Tsou, Yu An Shih, Chen-Hua Huang, Yao-Chung Fan
| Challenge: | Existing methods for cloze-style multiple choice questions (MCQs) distractor generation are based on knowledge bases and pre-trained language models. |
| Approach: | They propose to formulate cloze distractor generation task as Text2Text task and propose a pseudo Kullback-Leibler divergence for regulating the generation to consider item discrimination index in education evaluation. |
| Outcome: | The proposed model improves state-of-the-art performance from 10.81 to 22.00 (p@1 score) |