Class-Incremental Few-Shot Event Detection

arXiv:2404.01767v1 Announce Type: new
Abstract: Event detection is one of the fundamental tasks in information extraction and knowledge graph. However, a realistic event detection system often needs to deal with new event classes constantly. These new classes usually have only a few labeled instances as it is time-consuming and labor-intensive to annotate a large number of unlabeled instances. Therefore, this paper proposes a new task, called class-incremental few-shot event detection. Nevertheless, this task faces two problems, i.e., old knowledge forgetting …

abstract arxiv class cs.cl deal detection event extraction few-shot graph however incremental information information extraction instances knowledge knowledge graph labor tasks type