Dialogue text analysis method

Abstract

The invention discloses a dialogue text analysis method, medium and device, wherein the method comprises: acquiring historical dialogue information, and preprocessing the historical dialogue information to generate initial training samples; generating a first training sample and a first training sample according to the initial training samples Two training samples; model training is performed according to the first training sample to obtain a structural self-aware teacher model; model training is performed according to the second training sample to obtain a structural self-aware student model, and the structural relationship and the structural self-awareness teacher model are shortened. The structural relationship of the structural self-awareness student model is obtained to obtain the final structural self-awareness student model; the dialogue information to be parsed is obtained, and the dialogue information to be parsed is input into the final structural self-awareness student model to generate the dialogue rounds corresponding to the dialogue information to be parsed It can automatically parse the dialogue information to avoid error propagation caused by the introduction of explicit prediction results; at the same time, it can improve the effect of text parsing.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, and in particular, to a dialogue text parsing method, a computer-readable storage medium and a computer device. Background technique [0002] In the related art, when parsing dialogue texts, encoders are often used to learn the representation of each round of dialogue, and then splicing or adding methods are used to predict the textual relationship between the two rounds of dialogues. In addition, related technologies introduce the method of explicit historical round prediction results to assist the current round of chapter relationship prediction, which has the problem of error propagation, and the final chapter parsing effect is not good. SUMMARY OF THE INVENTION [0003] The present invention aims to solve one of the technical problems in the above technologies at least to a certain extent. Therefore, an object of the present invention is to propose a dialogue te...

AI Technical Summary

Problems solved by technology

[0002] In related technologies, when parsing dialogue chapters, an encoder is often used to learn the representation of each round of dialogue, and then through splicing or addition methods to predict the discourse relationship between two rounds of dialogue, and there is no structural relationship between the chapters in the model In addition, related technologies introduce explicit historical round prediction results to assist the current round of chapter relationship prediction, which has the problem of error propagation, and the final chapter parsing effect is not good.

Images