Event extraction method and system fusing dependency information and pre-trained language model

Abstract

The invention provides an event extraction method and system fusing dependency information and a pre-trained language model. The method comprises the steps of taking a dependency syntax tree of a sentence as input, learning dependency syntax features by using a graph convolutional neural network, adding a dependency relationship prediction task, capturing a more important dependency relationship in a multi-task learning mode, and finally enhancing underlying syntax expression by using a BERT pre-training language model to complete event extraction of Chinese sentences. Therefore, the performance of trigger word extraction and argument extraction under the event extraction task is improved.

Description

technical field [0001] The invention relates to the field of Internet technology, in particular to a method and system for extracting Chinese events that can be used in the fields of knowledge graphs and information extraction. Background technique [0002] Events, as a structured representation of information, refer to actual happenings involving certain participants. As a special class of information extraction tasks, the goal of event extraction is to extract instances of predefined event types from a given text. An event generally consists of two parts: a trigger word (Trigger) and an argument (Argument). The trigger word is the word in the text that can most clearly express the occurrence of the event, and is generally the core verb of the sentence where the event is located; the argument is related to the event, and An entity that plays a role in an event. Generally speaking, event extraction can be divided into two tasks: trigger word extraction and argument extract...

AI Technical Summary

Problems solved by technology

There are ways to use external knowledge bases or corpus resources as a supplement, and use weak supervision to expand the training data, but this type of method is limited to artificial rules and assumptions. Although the scale of the expanded data is large, the improvement of the performance of the extraction model is very limited.

[0007] To sum up, the main defect in the existing technology is that the dependent features and labeled data cannot be well modeled, which leads to insufficient extraction performance.

Images