Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification
文献类型:会议论文
作者 | Pengfei Cao; Yubo Chen; Yuqing Yang; Kang Liu; Jun Zhao |
出版日期 | 2021-11-07 |
会议日期 | November 7–11, 2021 |
会议地点 | Online |
英文摘要 | Event factuality indicates the degree of certainty about whether an event occurs in the real world. Existing studies mainly focus on identifying event factuality at sentence level, which easily leads to conflicts between different mentions of the same event. To this end, we study the problem of document-level event factuality identification, which determines the event factuality from the view of a document. For this task, we need to consider two important characteristics: Local Uncertainty and Global Structure, which can be utilized to improve performance. In this paper, we propose an Uncertain Local-to-Global Network (ULGN) to make use of these two characteristics. Specifically, we devise a Local Uncertainty Estimation module to model the uncertainty of local information. Moreover, we propose an Uncertain Information Aggregation module to leverage the global structure for integrating the local information. Experimental results demonstrate the effectiveness of our proposed method, outperforming the previous state-of-the-art model by 8.4% and 11.45% of F1 score on two widely used datasets. |
会议录出版者 | Association for Computational Linguistics |
源URL | [http://ir.ia.ac.cn/handle/173211/52150] |
专题 | 模式识别国家重点实验室_自然语言处理 |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Pengfei Cao,Yubo Chen,Yuqing Yang,et al. Uncertain Local-to-Global Networks for Document-Level Event Factuality Identification[C]. 见:. Online. November 7–11, 2021. |
入库方式: OAI收割
来源:自动化研究所
其他版本
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。