Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement
文献类型:会议论文
作者 | Xinyu Zuo2,3; Pengfei Cao2,3; Yubo Chen2,3; Kang Liu2,3; Jun Zhao2,3; Weihua Peng1; Yuguang Chen1 |
出版日期 | 2021 |
会议日期 | August 1-6, 2021 |
会议地点 | Bangkok, Thailand (Online) |
英文摘要 | Current models for event causality identification (ECI) mainly adopt a supervised framework, which heavily rely on labeled data for training. Unfortunately, the scale of current annotated datasets is relatively limited, which cannot provide sufficient support for models to capture useful indicators from causal statements, especially for handing those new, unseen cases. To alleviate this problem, we propose a novel approach, shortly named CauSeRL, which leverages external causal statements for event causality identification. First of all, we design a self-supervised framework to learn context-specific causal patterns from external causal statements. Then, we adopt a contrastive transfer strategy to incorporate the learned context-specific causal patterns into the target ECI model. Experimental results show that our method significantly outperforms previous methods on EventStoryLine and Causal-TimeBank (+2.0 and +3.4 points on F1 value respectively). |
语种 | 英语 |
源URL | [http://ir.ia.ac.cn/handle/173211/44856] |
专题 | 模式识别国家重点实验室_自然语言处理 |
作者单位 | 1.Beijing Baidu Netcom Science Technology Co., Ltd 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Xinyu Zuo,Pengfei Cao,Yubo Chen,et al. Improving Event Causality Identification via Self-Supervised Representation Learning on External Causal Statement[C]. 见:. Bangkok, Thailand (Online). August 1-6, 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。