Knowledge Commons of Institute of Automation,CAS
Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations | |
Ju YM(鞠一鸣)![]() ![]() ![]() ![]() ![]() | |
2021-11 | |
会议名称 | Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing |
会议日期 | 7th – 11th November 2021 |
会议地点 | Barceló Bávaro Convention Centre, Punta Cana, Dominican Republic |
摘要 |
Machine Reading Comprehension (MRC), which requires a machine to answer questions given the relevant documents, is an important way to test machines’ ability to understand human language. Multiple-choice MRC is one of the most studied tasks in MRC due to the convenience of evaluation and the flexibility of answer format. Post-hoc interpretation aims to explain a trained model and reveal how the model arrives at the prediction. One of the most important interpretation forms is to attribute model decisions to input features. Based on post-hoc interpretation methods, we assess attributions of paragraphs in multiple-choice MRC and improve the model by punishing the illogical attributions. Our method can improve model performance without any external information and model structure change. Furthermore, we also analyze how and why such a self-training method works. |
收录类别 | EI |
是否为代表性论文 | 是 |
七大方向——子方向分类 | 自然语言处理 |
国重实验室规划方向分类 | 可解释人工智能 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/52282 |
专题 | 多模态人工智能系统全国重点实验室_自然语言处理 |
通讯作者 | Zhao J(赵军) |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, CAS, Beijing, China 2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China |
推荐引用方式 GB/T 7714 | Ju YM,Zhang YZ,Tian ZX,et al. Enhancing Multiple-choice Machine Reading Comprehension by Punishing Illogical Interpretations[C],2021. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
2021.emnlp-main.295 (4223KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论