Semantic understanding model training method and device, computer equipment and storage medium

Abstract

The invention discloses a semantic comprehension model training method and device, computer equipment and a storage medium. The method comprises the steps of obtaining a total word sequence corresponding to a training text from a training set; randomly selecting a preset number of continuous word vectors from the total word sequence, replacing the continuous word vectors with a mask sequence to obtain an input word sequence, and taking the preset number of continuous word vectors as a test output word sequence; inputting the input word sequence into an encoder-attention-decoder model for training to obtain a prediction output word sequence; according to the difference between the prediction output word sequence and the test output word sequence, adjusting model parameters of the encoder-attention-decoder model to reduce the difference; and returning to input the input word sequence into the encoder-attention-decoder model for training to obtain a prediction output word sequence, continuing training, and stopping training until a preset training stop condition is met to obtain a semantic understanding model. According to the invention, the understanding accuracy of the computer to the natural language is improved.

Description

technical field [0001] The present application relates to the technical field of machine learning, in particular to a semantic understanding model training method, device, computer equipment and storage medium. Background technique [0002] With the development of artificial intelligence, computers need to understand a large amount of natural language when interacting with humans. The research of natural language model is the current research hotspot in the field of Internet and artificial intelligence. The current mainstream natural language understanding mainly adopts the method based on statistical rule learning to obtain language statistical knowledge from a large number of language sample data to establish a language understanding model. However, in actual use, due to the poor generalization of statistical rules, when the content or format of natural language text changes, the corresponding statistical rules will become invalid, and the understanding ability of the lan...

AI Technical Summary

Problems solved by technology

[0003] The main purpose of this application is to provide a semantic understanding model training method, device, computer equipment and storage medium, aiming to solve the problem of low accuracy of computer understanding of natural language in the prior art

Images