Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Text classification method and system for lifelong learning

A text classification and lifelong technology, applied in the text classification method and system field of lifelong learning, to achieve the effect of reducing time complexity

Active Publication Date: 2022-05-17
FOSHAN UNIVERSITY
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to propose a text classification method and system for lifelong learning, to solve one or more technical problems in the prior art, and at least provide a beneficial choice or create conditions

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
  • Text classification method and system for lifelong learning
  • Text classification method and system for lifelong learning
  • Text classification method and system for lifelong learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0079] The idea, specific structure and technical effects of the present invention will be clearly and completely described below in conjunction with the embodiments and accompanying drawings, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0080] In the description of the present invention, several means one or more, and multiple means two or more. Greater than, less than, exceeding, etc. are understood as not including the original number, and above, below, within, etc. are understood as including the original number. If the description of the first and second is only for the purpose of distinguishing the technical features, it cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implic...

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 invention provides a lifelong learning text classification method and system, and the method comprises the steps: taking a pre-training language model as a text classification model, and carrying out the training of the text classification model through a task sequence, and obtaining a lifelong learning model; setting a storage memory; the method comprises the following steps of: firstly, carrying out sparse experience playback on a lifelong learning model to store memory, carrying out fine tuning on the lifelong learning model by using a sparse experience playback mode according to playback frequency and a storage rate, carrying out fine tuning on the lifelong learning model again, and then carrying out prediction output on an input text by using the lifelong learning model, thereby realizing the following purposes: firstly, reducing time complexity so as to save training time; the text classification accuracy is improved; and disastrous forgetting is relieved.

Description

technical field [0001] The invention belongs to the technical field of text data processing and character processing, and in particular relates to a text classification method and system for lifelong learning. Background technique [0002] Lifelong learning is a continuous learning process, and its research fields include lifelong supervised learning, lifelong reinforcement learning, open learning, etc. This paper mainly studies in the field of lifelong supervised learning, when the model is trained on new task data after completing a series of N supervised learning tasks, the neural network usually forgets the knowledge learned in the previous task, which means that the weight of the new task The weights of previous tasks may be overwritten, thereby reducing the performance of the model on previous tasks and causing catastrophic forgetting. After learning the knowledge of the first N categories, the lifelong learning text classification model has the ability to continue le...

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
IPC IPC(8): G06F16/35G06N3/04G06N3/08
CPCG06F16/353G06F16/355G06N3/08G06N3/047G06N3/045
Inventor 孔蕾蕾彭泽阳齐浩亮韩咏韩中元
Owner FOSHAN UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products