Implicit discourse relationship analysis method and system

Abstract

The invention provides an implicit discourse relationship analysis method based on a semantic-syntax dual-path graph convolutional network, and belongs to the technical field of natural language processing application. The method comprises the following steps that of firstly, conducting word segmentation is conducted on corpora; constructing a word list and the like for preprocessing, and then initializing word vectors by utilizing GloVe; and respectively inputting the two initialized arguments into Bi-LSTM codes to obtain word representations of the Bi-LSTM codes fused with the context information. T; using the Bi-LSTM output is used to subsequently initialize representations of graph nodes in a binary channel graph convolutional network. , wWherein the dual-path graph convolutional network comprises two GCN networks, extracting corresponding features from the interaction structure graph and the syntax structure graph respectively, and splicing different features obtained by two pathsfor classification. And ; updating parameters in the model to convergence by adopting an Adam algorithm, and completing the analysis of the implicit discourse relationship by using the parameter withthe optimal performance.

Description

technical field [0001] The invention relates to an implicit discourse relationship analysis method and system, belonging to the technical field of natural language processing applications. Background technique [0002] Discourse relationship analysis is an important task in natural language processing, which aims to identify and classify intersentence relationships in multi-sentence texts. Effective identification and application of discourse relations can improve the performance of various downstream natural language processing tasks, such as machine translation, text summarization, etc. Discourse relations can be divided into explicit and implicit according to whether there are discourse connectives (such as "but" and "so") between sentences. Among them, the identification of implicit discourse relations without connectives is the main difficulty. Due to the lack of indication of connectives, implicit discourse relations can only identify the logical relationship between ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the following two problems that existed in the past in the implicit discourse relationship analysis: 1) for existing method neglects the problem of the interactive semantics between the modeling sentence pair

2) The method for ordinary neural networks does not consider the problem of the original syntactic structure information of the sentence

Images