Multi-model training method, abstract segmentation method, text segmentation method and device

Abstract

The invention relates to the technical field of artificial intelligence, and discloses a multi-model training method, which comprises the following steps of: dividing texts in a training text set into single sentences to obtain a training single sentence set; performing feature extraction on the training single sentence set to obtain a training single sentence vector set; extracting paragraph coding features and abstract coding features of the training single sentences in the training single sentence vector set; and carrying out first training on a pre-constructed text segmentation model by utilizing the training single sentence vector set and the abstract coding features, and carrying out second training on a pre-constructed text abstract extraction model by utilizing the training single sentence vector set and the paragraph coding features to obtain a standard text segmentation model and a standard text abstract extraction model. In addition, the invention also relates to an abstract extraction method, a text segmentation method and device, equipment and a storage medium. According to the method, the model accuracy of the text segmentation model and the abstract extraction model obtained through training can be improved, and the efficiency of obtaining the text segmentation model and the abstract extraction model obtained through training can be improved.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, and in particular to a multi-model training method, a summary segmentation method, a text segmentation method, a device, an electronic device, and a storage medium. Background technique [0002] Text segmentation and summary extraction are common processing methods for text processing. In the prior art, a text summary extraction model and a text segmentation model are usually trained separately. Specifically, the existing technology for text segmentation tasks is to use the Jaccard similarity analyzer to find out the distance between consecutive sentences, and if the distance between them is less than a given value, the consecutive sentences will be combined into a paragraph . However, this segmentation method only performs segmentation from a single dimension of similarity between sentences, which easily leads to inaccurate segmentation results. [0003] The text summ...

AI Technical Summary

Problems solved by technology

However, this segmentation method only segments from a single dimension of similarity between sentences, which can easily lead to inaccurate segmentation results

[0003] The text summary extraction model used in the existing text summary extraction methods usually only considers the position of the sentence, and extracts the first few sentences of a text to form a summary. This method is more suitable for news texts, and the scope of application of the text summary extraction model Not wide, when extracting paragraphs other than specific types of text (such as news text), the extraction results are often inaccurate

In summary, the acquisition efficiency of the text segmentation model and the text summary extraction model in the prior art is not high, and the accuracy of the model is not high

Images