Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and system for assisting text annotation

A text and input text technology, applied in the field of auxiliary text labeling, can solve problems such as manual review risks, high labor costs, poor consistency, etc.

Pending Publication Date: 2019-12-24
ADVANCED NEW TECH CO LTD
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in the existing system, it is necessary to manually review and mark whether the content is risky, which category it belongs to, etc.
However, due to the large amount of text and / or data that needs to be manually reviewed and / or marked, it requires a very large labor cost and the consistency of the review and / or mark is poor

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
  • Method and system for assisting text annotation
  • Method and system for assisting text annotation
  • Method and system for assisting text annotation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The detailed description, set forth below in connection with the accompanying drawings, is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details to provide a thorough understanding of various concepts. It will be apparent, however, to one skilled in the art that these concepts may be practiced without these specific details.

[0035] refer to figure 1 , which shows a structural diagram of an example model network 100 for text classification according to an embodiment of the present disclosure.

[0036] According to an embodiment of the present disclosure, a model network (ie, a neural network based on an attention mechanism) may include an input layer, a Bi-RNN stacked with two layers, an attention layer, and an output layer. Such as figure 1 As shown, the bottom is used to receive the input vector (for exa...

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 relates to a method and a system for assisting text annotation. The method comprises the steps of obtaining a text; preprocessing the text to generate an input vector for a neural network based on an attention mechanism; inputting the generated input vector into the neural network based on the attention mechanism to classify and extract keywords in the input text; and outputting anddisplaying a processing result of the attention mechanism-based neural network, the result including probabilities of the input text belonging to the categories and the keywords included in the inputtext.

Description

technical field [0001] The present disclosure relates to methods and systems for assisting text annotation. Background technique [0002] With the continuous progress and development of Internet technology, the self-media era in which individuals release information independently has arrived, making content sources more complex and increasing in number. In content security prevention and control, various illegal content including illegal advertisements, pornography, gambling, drugs, and politics need to be blocked from publishing. However, due to the large amount of content, this brings challenges to content classification review. In addition, with the advent of the era of big data, there is a need to label large amounts of data. [0003] However, in the existing system, it is necessary to manually review and mark whether the content is risky, which category it belongs to, and so on. However, due to the large amount of text and / or data that needs to be manually reviewed a...

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): G06F17/27G06F17/24G06F16/35G06F16/958
CPCG06F16/355G06F16/958
Inventor 郭亚祝慧佳赵智源周书恒
Owner ADVANCED NEW TECH CO LTD