Sudden Event Prediction Based on Event Knowledge Graph

Event prediction is a knowledge inference problem that predicts the consequences or effects of an event based on existing information. Early work typically modeled context to predict what would happen next. Moreover, predicted outcome was often singular. These studies had difficulty coping with both problems predicting sudden events in unknown contexts and outcomes consisting multiple events. To address these two better, we present heterogeneous graph model (HGEP), which graph. cope situation missing contexts, propose representation learning method transformer. We generate scenario representations from arguments initial other related concurrent for prediction. improve ability HGEP through prior provided by models obtain outcomes, design scoring function calculate score occurrence probability each class. The classes scores higher than priori values are adopted as outcomes. In this paper, create domain transportation experiment. experimental results show can effectively make predictions has more accurate matching rate precision baseline model.