Text processing method and device, electronic equipment and readable storage medium

Abstract

The embodiment of the invention provides a text processing method and device, electronic equipment and a readable storage medium, and relates to the field of artificial intelligence, and the method comprises the steps: obtaining a plurality of initial texts, and constructing a training data set based on the plurality of initial texts; training the initial neural network model based on the training data set until a value of a target function of the model meets a training ending condition; using the feature extraction module after training is finished as a text feature extraction module of a text similarity judgment model, training the text similarity judgment model again, obtaining a final text similarity judgment model, and the text similarity judgment model comprises a text feature extraction module and a second text similarity prediction module which are cascaded. The training data set constructed in the embodiment of the invention is weak supervision text similar corpora, and label data does not need to be manually labeled, so that the manpower and time cost can be effectively saved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, specifically, the present application relates to a text processing method, device, electronic equipment and readable storage medium. Background technique [0002] With the development of natural language processing technology, pre-trained language models are widely used in downstream tasks such as text matching, information extraction, and intelligent question answering due to their effectiveness. Although there are already some solutions to improve the expression ability of the pre-training model through pre-training, the current methods all require a large amount of labeled data to achieve the pre-training task, and the existing pre-training task and downstream tasks usually have problems. The large difference leads to the unsatisfactory effect of pre-training, and the existing pre-training methods still need to be improved. Contents of the invention [0003] The pr...

AI Technical Summary

Problems solved by technology

Although there are already some solutions to improve the expression ability of the pre-training model through pre-training, the current methods all require a large amount of labeled data to achieve the pre-training task, and the existing pre-training task and downstream tasks usually have problems. The large difference leads to the unsatisfactory pre-training effect, and the existing pre-training methods still need to be improved

Images