Siamese capsule network with position correlation and integrating articles of law for Chinese similar case matching

Abstract

The purpose of the Chinese similar case matching task is to compare the similarity of two case texts with a given anchor text and find out which text is more similar to the anchor text. In the area of law, it plays an important role and has been of interest to many researchers. Previous approaches have compared legal texts only at the text semantic level, without incorporating article information of law. In addition, the position correlation of words in case texts is often important, but it has not been considered in previous approaches. This paper proposes a method which extracts features from the semantic similarity level and from the level of related articles of law, respectively, to enable similarity comparisons of legal case texts. When similarity comparisons are made at the semantic similarity level, a novel capsule network method is proposed based on siamese structure that introduces the position correlation and the routing mechanism within the capsule network is improved so that deep text features between case pairs can be learned. When similarity comparisons are made at the level of related articles of law, related articles of law are selected and coded and interacted with the case text features to generate legal features. Experiment is conducted with a real-world legal text dataset, and the proposed model outperformed all baseline models, demonstrating effectiveness of the proposed model. Further, to confirm the generality of the improved capsule network proposed in the paper on long text datasets, this paper also carried out experiments on two long text datasets, demonstrating effectiveness of the improved capsule network proposed in the model.