Processing method, device and equipment for sentence vector generation model based on artificial intelligence

Abstract

The invention discloses a processing method of a sentence vector generation model based on artificial intelligence, which is applied to the technical field of artificial intelligence and is used for solving the technical problems of low learning efficiency of text sentence vectors and poor expression accuracy of the sentence vectors. The method provided by the invention comprises the following steps: acquiring a text sample which does not carry a sample label; inputting the text sample into a BERT module in a sentence vector generation model to be trained, and outputting an intermediate feature of the text sample through the BERT module; selecting different discarding masks for the middle features of the same text sample to execute dropout discarding operation, and obtaining middle feature vectors, corresponding to the discarding masks, of the same text sample; determining the intermediate feature vectors belonging to the same text sample as positive samples, and determining the intermediate feature vectors belonging to different text samples as negative samples; and training the sentence vector generation model according to the positive sample, the negative sample and a loss function to obtain a trained sentence vector generation model.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a processing method, device, computer equipment and storage medium for a sentence vector generation model based on artificial intelligence. Background technique [0002] In natural language processing, especially in Chinese language processing, how to learn sentence vectors is the most basic and important link. Sentence vectors can be applied to text search and FAQ (Frequently Asked Questions, frequently asked questions) matching , semantic recall, text sorting and other scenarios, in recent years, how to learn sentence vectors has become more and more a research hotspot. [0003] Most of the current sentence vector learning methods are based on labeled sample data, which requires a lot of manpower to add sample labels, while pre-training-based methods, such as Bert-based methods, suffer from anisotropy problems, resulting in The learning process of sente...

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a processing method, device, computer equipment, and storage medium for a sentence vector generation model based on artificial intelligence, so as to solve the technical problems of low learning efficiency of text sentence vectors and lack of representation accuracy of sentence vectors

Images