2024-06-24
【學術亮點-頂級會議論文】基於 Text2Text 模型與 Pseudo KL Divergence 之干擾選項生成
字體大小
小
中
大
【學術亮點-頂級會議論文】基於 Text2Text 模型與 Pseudo KL Divergence 之干擾選項生成
AI core Technology: Advanced Research and Resource Integration Platform or AI Technology
【Department of Computer Science and Engineering / Yao-Chung Fan / Associate Professor】
核心技術：AI核心技術之進階研究與資源整合平台【資訊工程學系范耀中副教授】
上架日期：2023/7/9-7/14
AI core Technology: Advanced Research and Resource Integration Platform or AI Technology
【Department of Computer Science and Engineering / Yao-Chung Fan / Associate Professor】
核心技術：AI核心技術之進階研究與資源整合平台【資訊工程學系范耀中副教授】
| 論文篇名 | 中文：基於 Text2Text 模型與 Pseudo KL Divergence 之干擾選項生成 英文：Distractor Generation based on Text2Text Language Models with Pseudo Kullback-Leibler Divergence Regulation |
| 期刊名稱 | Findings of the Association for Computational Linguistics: ACL 2023 (指標清單期刊) |
| 發表年份, 卷數, 起迄頁數 | The 61st Annual Meeting of the Association for Computational Linguistics (ACL 203) in Toronto, Canada from July 9th to 14th, 2023 |
| 作者 | Hui-Juan Wang, Kai-Yu Hsieh, Han-Cheng Yu, Jui-Ching Tsou, Yu-An Shih, Chen-Hua Huang, Yao-Chung Fan(范耀中)∗ |
| DOI | 10.18653/v1/2023.findings-acl.790 |
| 英文摘要 | In this paper, we address the task of cloze-style multiple choice question (MCQs) distractor generation. Our study is featured by the following designs. First, we propose to formulate the cloze distractor generation as a Text2Text task. Second, we propose pseudo Kullback-Leibler Divergence for regulating the generation to consider the item discrimination index in education evaluation. Third, we explore the candidate augmentation strategy and multi-tasking training with cloze-related tasks to further boost the generation performance. Through experiments with benchmarking datasets, our best perfomring model advances the state-of-the-art result from 10.81 to 22.00 (p@1 score). |
