Cheng Jing, Shanshan Xue

(Qingdao University of Science and Technology)

Abstract：

Event extraction is the process of automatically extracting event information of interest to users from unstructured natural language text and representing it in a structured form Event extraction is an important direction in natural language processing and understanding, with high application value in various fields such as government public affairs management, financial business, biomedical science, etc According to the degree of dependence on manually annotated data, current event extraction methods based on deep learning are mainly divided into two categories: supervised and remote supervised learning methods A comprehensive review was conducted on event extraction techniques in current deep learning A systematic summary of recent research on supervised methods such as CNN, RNN, GAN, GCN, and remote supervision was conducted, and the performance of different deep learning models was compared and analyzed in detail Finally, the challenges faced by event extraction were analyzed, and the research trends were discussed.

Key Words：

event extraction; supervised learning; deep learning; remote supervision; information extraction