Text classification model construction method and text classification method and device

Abstract

The invention discloses a text classification model construction method and device and a text classification method and device, and the method comprises the steps: obtaining training text data and a plurality of pieces of preset label attribute information corresponding to a field to which the training text data belongs; inputting the training text data and a plurality of pieces of preset label attribute information into a reading understanding model to obtain text interaction representation between each piece of training text data and each piece of preset label attribute information; inputting each text interaction representation into the feature extraction model to obtain text key features; inputting the text key features into an initial classification model for classification and identification to obtain a probability value of each piece of training text data belonging to each piece of preset label attribute information, and obtaining a classification result according to the probability value; and training model parameters of the initial classification model according to a classification result until a loss function value of the initial classification model meets a target condition to obtain a target text classification model.

Description

technical field [0001] The present invention relates to the technical field of data processing and machine learning, in particular to a text classification model building method, a text classification method and a device. Background technique [0002] Text classification refers to the use of computers to automatically classify and mark text collections according to certain classification systems or standards. In related technologies, when classifying text, the semantic features of the text are usually extracted according to the text classification model, but this method requires a large number of training samples, and the text data corresponding to different text label categories is unbalanced, resulting in the generalization of the model Therefore, it is urgent to propose a text classification model construction method to reduce training samples and improve model generalization ability. Contents of the invention [0003] Therefore, the technical problem to be solved by t...

AI Technical Summary

Problems solved by technology

[0003] Therefore, the technical problem to be solved by the present invention is to overcome the defect in the prior art that the semantic features of the text are extracted according to the text classification model to classify the text and the generalization ability of the text is poor, thereby providing a text classification model construction method and a text classification method and device

Images