Implicit discourse relationship classification method

Abstract

The invention relates to an implicit discourse relationship classification method. The method comprises the following steps: for first discourse information and second discourse information to be classified, based on an implicit discourse relationship classification model, obtaining a semantic interaction graph structure of semantic information in the first discourse information and the second discourse information; for the semantic interaction graph structure, obtaining semantic features corresponding to the first discourse information and the second discourse information; projecting the obtained semantic features into a hyperbolic space by means of index mapping, and obtaining a classification result of the first discourse information and the second discourse information, wherein the classification model based on the implicit discourse relationship is a model which is pre-established and trained and comprises a context presentation layer, a semantic learning layer, a convolution layer, an aggregation layer and a prediction layer; and enabling the context presentation layer and the semantic learning layer to execute a process of obtaining a semantic interaction graph structure, enabling the semantic learning layer, the convolution layer and the aggregation layer to execute a process of obtaining semantic features, and enabling the prediction layer to execute a process of obtaining a classification result.

Description

technical field [0001] The invention relates to the technical field of classification of implicit textual relations, in particular to a classification method of implicit textual relations. Background technique [0002] Discourse relation classification aims to identify logical relations between two text spans. It is a fundamental task of discourse parsing and is beneficial to many natural language processing tasks, such as machine translation, question answering systems, and text generation. According to whether a text instance contains connective words, the task of discourse relationship classification can be divided into two types: explicit discourse relation classification in which sentences contain connective words and implicit discourse relation classification in which sentences do not contain connective words. Using only connectives as features, the explicit discourse relationship classification task achieves over 93% accuracy. For implicit discourse relationship cla...

AI Technical Summary

Problems solved by technology

[0005] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a classification method for implicit discourse relations, which solves the technical problem that the existing methods do not consider syntactic structure and context information, resulting in inaccurate classification results of discourse relations

Images