Causality is an important type of logical relation between events that expresses high-level logical informa-tion and reveals event development patterns.The identification of event causality contained in texts via natural lan-guage processing methods is important in providing interpretability and robustness for various downstream applica-tions such as question answering and event prediction.Therefore,we comprehensively review both the identification and application of event causality.First,to clarify the research scope,the basic concept of causality and the task def-inition of event causality identification(ECI)are introduced.Then,common-used datasets for ECI are summarized and further explored to figure out the inherent difficulties.Subsequently,following the technology development timeline,related ECI methods fall into three categories:rule mining,feature engineering,and deep learning.Based on this,a systematic and structured introduction,comparison,and summary are provided.Moreover,a brief over-view of the application scenario of event causality is given to further show the significant application value of causal knowledge.Finally,the existing challenges and future research directions on ECI are discussed.
关键词
因果关系识别/自然语言处理/深度学习/数据增强/知识提升
Key words
event causality identification/natural language processing/deep learning/data augmentation/knowledge enhancement
维普
万方数据