Method for extracting case elements in news text sentences based on case correlation joint learning and graph convolution

The invention relates to a method for extracting case elements in news text sentences based on case correlation joint learning and graph convolution, and belongs to the technical field of natural language processing. The method comprises the following steps: firstly, analyzing core components in a sentence to be extracted by using a dependency syntax analysis tool; constructing alternative elementgroups, performing feature modeling on the dependency relationship of the candidate elements through a graph convolutional neural network; capturing the internal relevance of the candidate element, performing feature modeling on a sentence to be extracted in time sequence logic, learning the correlation features of the case field, and finally judging whether the candidate element is a group of case elements by integrating the features of the candidate element and the features of the sentence where the candidate element is located. According to the method, the case domain correlation and the intrinsic correlation of t