Knowledge Commons of Institute of Automation,CAS
Scene Restoring for Narrative Machine Reading Comprehension | |
Zhixing Tian1,2; Yuanzhe Zhang1; Kang Liu1,2; Jun Zhao1,2; Yantao Jia3; Zhicheng Sheng3 | |
2020 | |
会议名称 | Conference on Empirical Methods in Natural Language Processing (EMNLP 2020) |
会议日期 | Nov 16, 2020 - Nov 20, 2020 |
会议地点 | Online |
摘要 | This paper focuses on machine reading comprehension for narrative passages. Narrative passages usually describe a chain of events. When reading this kind of passage, humans tend to restore a scene according to the text with their prior knowledge, which helps them understand the passage comprehensively. Inspired by this behavior of humans, we propose a method to let the machine imagine a scene during reading narrative for better comprehension. Specifically, we build a scene graph by utilizing Atomic as the external knowledge and propose a novel Graph Dimensional- Iteration Network (GDIN) to encode the graph. We conduct experiments on the ROCStories, a dataset of Story Cloze Test (SCT), and CosmosQA, a dataset of multiple choice. Our method achieves state-of-the-art. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 自然语言处理 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/40591 |
专题 | 多模态人工智能系统全国重点实验室_自然语言处理 |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences 3.Huawei Technologies Co., Ltd |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Zhixing Tian,Yuanzhe Zhang,Kang Liu,et al. Scene Restoring for Narrative Machine Reading Comprehension[C],2020. |
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 | ||
390_Paper.pdf(881KB) | 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