Identification model training method and device and text identification method and device

Abstract

The invention provides an identification model training method and device and a text identification method and device. The identification model training method comprises the steps of obtaining a training text; inputting the training text into a to-be-trained recognition model, and encoding the training text through a language module in the to-be-trained recognition model to obtain a feature vector; respectively inputting the feature vector into a filling module and an intention module in the to-be-trained recognition model for processing, and determining a relation weight of the filling module and the intention module according to a processing result; adjusting the filling module and the intention module based on the relation weight, and obtaining a first loss value of the filling module and a second loss value of the intention module according to an adjustment result; and performing iterative training on the to-be-trained recognition model based on the first loss value and the second loss value until a training stop condition is met, and obtaining a target recognition model.

Description

technical field [0001] The present application relates to the technical field of natural language processing, in particular to a recognition model training method and device, and a text recognition method and device. Background technique [0002] Natural Language Processing (NLP) is an important direction in the field of computer science and artificial intelligence. It studies various theories and methods that can realize effective communication between humans and computers using natural language. When the prior art understands speech information and infers internal relations, most of them are realized by the RNN (Recurrent Neural Network, RNN) model based on Attention; although the purpose of semantic understanding can be achieved, the pre-preparation process of the model consumes a lot of time, and The prepared model needs to be retrained after a period of application, which not only consumes time but also consumes resources, so an effective solution is urgently needed to ...

AI Technical Summary

Problems solved by technology

When the prior art understands speech information and infers internal relations, most of them are realized by the RNN (Recurrent Neural Network, RNN) model based on Attention; although the purpose of semantic understanding can be achieved, the pre-preparation process of the model consumes a lot of time, and The prepared model needs to be retrained after a period of application, which not only consumes time but also consumes resources, so an effective solution is urgently needed to solve the above problems

Images