A method and system for understanding semantically distributed text with adaptive architecture

An adaptive classification and self-adaptive technology, applied in semantic analysis, natural language data processing, unstructured text data retrieval, etc., can solve problems such as poor performance of classification models, solve key information sensitive problems, and solve categories that cannot Completely independent questions, the effect of disambiguating questions

Active Publication Date: 2021-02-26
前海企保科技(深圳)有限公司
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this case, classification models such as pre-training tend to perform poorly

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 method and system for understanding semantically distributed text with adaptive architecture
  • A method and system for understanding semantically distributed text with adaptive architecture
  • A method and system for understanding semantically distributed text with adaptive architecture

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0043] refer to Figure 1 to Figure 3 , the present invention provides an adaptive architecture semantic distribution text understanding method, comprising steps:

[0044] S1. Encode the input text through the text basic encoder module to obtain text feature representation;

[0045] S2. The text feature representation is processed by a multi-head attention mechanism through the semantic association key distribution representation module to form a self-attention representation of the text feature representation;

[0046] S3. Using the architecture-adaptive classification network module to automatically select a classification network for the self-attention representation of the text feature representation, to achieve the final classification. ...

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 present invention relates to a text understanding method and system of self-adaptive architecture semantic distribution. The main modules included in the self-adaptive architecture semantic distribution text understanding system include a text basic encoder, a semantic association key distribution representation module, and an architecture self-adaptive classification network module. The present invention utilizes the context multi-head attention semantic distribution representation in the semantic association key distribution representation module, which can better utilize the context information and eliminate the ambiguity of the context expression; meanwhile, through the key information multi-head attention semantic distribution representation, keywords, Phrases and other key information to solve the problem that key information in subdivided fields is sensitive to classification tasks. The architecture-adaptive classification network module can adaptively select the classification network layer according to the similarity of classification categories, so that similar classifications share weight parameters, and classifications with large differences in classification categories do not share weights, so that classification can be better solved. A problem where categories cannot be completely independent.

Description

technical field [0001] The invention relates to the field of classification and processing of natural language texts, in particular to a text understanding method and system for adaptive framework semantic distribution. Background technique [0002] In the Internet era of information explosion, any website needs to process a large amount of text data, and it is essential to classify and structure the information, and manual processing has completely failed to meet the efficiency requirements of the Internet age. As a natural language processing The most basic task of text classification is important and indispensable. The automatic classification of text can summarize and concentrate a large amount of information, further structure the text information, save manpower and time costs, increase the attention to target information, and thus improve the speed of information processing and decision-making efficiency. [0003] Common applications of text classification include new...

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): G06F40/289G06F40/30G06F16/33G06F16/35G06K9/62G06N3/04G06N3/08
CPCG06F40/289G06F40/30G06F16/3344G06F16/35G06N3/08G06N3/047G06N3/045G06F18/2415G06F18/241
Inventor 庞文君杨猛黄志青
Owner 前海企保科技(深圳)有限公司
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