Reading understanding type news text event extraction method based on BERT model

The invention provides a reading understanding type news text event extraction method based on a BERT class model. The reading understanding type news text event extraction method comprises the steps: collecting Chinese news text corpora, and obtaining an event type table and an argument table; sorting the event type table and the argument table; designing different problems according to the argument table; dividing a training set, a verification set and a test set; labeling a training set and a verification set; inputting the training set and the verification set into a BERT type model for training and verification, and respectively obtaining an event type multi-classification model, a binary classification model with and without answers to questions or not, and an argument extraction model; and predicting the test set by using the event type multi-classification model, the binary classification model with and without the answers to the questions and the argument extraction model to obtain the event type of