System and method for extracting few sample events of prototype network

The invention discloses a system and a method for extracting few sample events of a prototype network in the technical field of natural language processing. The method comprises the following steps: acquiring an inquiry set containing test data; splicing the single test data in the inquiry set with the label candidate items respectively and then sending the spliced data to a Bert encoder, and taking the corresponding CLS representation as the representation of the single test data; reading the support sets of all categories, and calculating to obtain candidate model prototypes of all categories in the inquiry set; and based on the prototypes of all category candidates, calculating to obtain a target category of single test data in the inquiry set. According to the method, better accuracy is provided in the field of few-sample event extraction, and a few-sample landing practice scheme is provided. 本发明公开了自然语言处理技术领域的一种原型网络的少样本事件抽取系统及方法，包括：获取包含测试数据的询问集；将询问集中的单个测试数据分别与标签候选项进行拼接后送到Bert编码器中，取相应的CLS表示作为单个测试数据的表示；读取所有