Enhancing Distractor Generation for Multiple-Choice Questions with Retrieval Augmented Pretraining and Knowledge Graph Integration
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916295396556800 |
|---|---|
| author | Yu, Han-Cheng Shih, Yu-An Law, Kin-Man Hsieh, Kai-Yu Cheng, Yu-Chen Ho, Hsin-Chih Lin, Zih-An Hsu, Wen-Chuan Fan, Yao-Chung |
| author_facet | Yu, Han-Cheng Shih, Yu-An Law, Kin-Man Hsieh, Kai-Yu Cheng, Yu-Chen Ho, Hsin-Chih Lin, Zih-An Hsu, Wen-Chuan Fan, Yao-Chung |
| contents | In this paper, we tackle the task of distractor generation (DG) for multiple-choice questions. Our study introduces two key designs. First, we propose \textit{retrieval augmented pretraining}, which involves refining the language model pretraining to align it more closely with the downstream task of DG. Second, we explore the integration of knowledge graphs to enhance the performance of DG. Through experiments with benchmarking datasets, we show that our models significantly outperform the state-of-the-art results. Our best-performing model advances the F1@3 score from 14.80 to 16.47 in MCQ dataset and from 15.92 to 16.50 in Sciq dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13578 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Distractor Generation for Multiple-Choice Questions with Retrieval Augmented Pretraining and Knowledge Graph Integration Yu, Han-Cheng Shih, Yu-An Law, Kin-Man Hsieh, Kai-Yu Cheng, Yu-Chen Ho, Hsin-Chih Lin, Zih-An Hsu, Wen-Chuan Fan, Yao-Chung Computation and Language In this paper, we tackle the task of distractor generation (DG) for multiple-choice questions. Our study introduces two key designs. First, we propose \textit{retrieval augmented pretraining}, which involves refining the language model pretraining to align it more closely with the downstream task of DG. Second, we explore the integration of knowledge graphs to enhance the performance of DG. Through experiments with benchmarking datasets, we show that our models significantly outperform the state-of-the-art results. Our best-performing model advances the F1@3 score from 14.80 to 16.47 in MCQ dataset and from 15.92 to 16.50 in Sciq dataset. |
| title | Enhancing Distractor Generation for Multiple-Choice Questions with Retrieval Augmented Pretraining and Knowledge Graph Integration |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.13578 |