A model training method and related device

A technology of model training and training text, applied in neural learning methods, biological neural network models, unstructured text data retrieval, etc., can solve problems such as long training time and slow model convergence speed, and achieve the effect of improving training speed

Active Publication Date: 2022-03-25
TENCENT TECH (SHENZHEN) CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The inventors of the present application found that both the BERT model and the ELECTRA model have the problems of slow model convergence and long training time

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A model training method and related device
  • A model training method and related device
  • A model training method and related device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiment of the application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiment of the application. Obviously, the described embodiment is only It is a part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.

[0036] The terms "first", "second", "third", "fourth", etc. (if any) in the description and claims of this application and the above drawings are used to distinguish similar objects, and not necessarily Used to describe a specific sequence or sequence. It is to be understood that the data so used are interchangeable under appropriate circumstances such that the em...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The embodiment of the present application discloses a model training method and related devices in the field of artificial intelligence, wherein the method includes: obtaining basic training text, splitting and processing the basic training text to obtain a sequence of basic text fragments; Determine the text segment to be replaced in the sequence, select the target replacement text segment from the candidate segment set corresponding to the text segment to be replaced, use the target replacement text segment to replace the text segment to be replaced in the basic text segment sequence, and obtain the target text segment sequence; The target text segment sequence and its corresponding label annotation results are used as training samples, and the label annotation results include the label tags corresponding to each text segment in the target text segment sequence; the text semantic recognition model is trained based on the training samples; the text semantic recognition model is used for input A sequence of text fragments predicts whether each text fragment has been replaced. This method can improve the speed of model training.

Description

technical field [0001] The present application relates to the technical field of artificial intelligence, in particular to a model training method and related devices. Background technique [0002] Text semantic recognition technology is now widely used in many application scenarios, such as text classification, sentiment analysis, intent recognition, and so on. When applying text semantic recognition technology in various application scenarios, it is usually necessary to use the text semantic recognition model to determine the global semantic vector of the text to be processed, and then perform specific tasks in the application scenario according to the global semantic vector of the text to be processed. [0003] In related technologies, commonly used text semantic recognition models include the BERT (Bidirectional Encoder Representations from Transformers) model and the ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) model. The inve...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06F40/30G06F16/35G06N3/04G06N3/08
CPCG06F40/30G06F16/353G06N3/08G06N3/047G06N3/045
Inventor 刘绩刚徐灿杨迪
Owner TENCENT TECH (SHENZHEN) CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap