Word distributed representation learning system based on emotional knowledge enhancement

A learning system and distributed technology, applied in natural language data processing, text database query, instruments, etc., can solve problems such as limited effect of emotional knowledge and lack of emotional dependence information

Active Publication Date: 2022-04-29
GUILIN UNIV OF ELECTRONIC TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Therefore, some scholars hope to improve the effect of sentiment analysis by integrating sentiment dictionaries. However, the effect of these sentiment knowledge is very limited, and they lack the emotional dependence information in the professional field.
Can't solve the problem of "emotional information target dependence" in the professional field well

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
  • Word distributed representation learning system based on emotional knowledge enhancement
  • Word distributed representation learning system based on emotional knowledge enhancement
  • Word distributed representation learning system based on emotional knowledge enhancement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] like figure 1 As shown, the present embodiment 1 provides a word distributed representation learning system based on emotional knowledge enhancement, which includes an emotional knowledge integration framework and a weakly supervised knowledge generation framework; the emotional knowledge integration framework includes a knowledge query module, a knowledge integration module and a word The representation generation module; the weakly supervised knowledge generation framework is used to generate the domain sentiment dictionary DSD, which integrates the resources of three parts: the unlabeled text of the target domain, the domain independent sentiment dictionary and the label of the target domain text.

[0044] figure 1 The Chinese and English translations are as follows:

[0045] input0 original input text

[0046] input1 knowledge-augmented text

[0047] Knowledge Context Attention knowledge global attention

[0048] BERTBidirectional Encoder Representations from Tr...

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 the technical field of emotion detection and emotion analysis, in particular to a word distributed representation learning system based on emotion knowledge enhancement, which comprises an emotion knowledge integration framework and a weak supervision knowledge generation framework, the emotional knowledge integration framework comprises a knowledge query module, a knowledge integration module and a word representation generation module; the weak supervision knowledge generation framework is used for generating a domain sentiment dictionary DSD, and the DSD integrates resources of three parts, namely, a non-label text of a target domain, a domain-independent sentiment dictionary and a label of the target domain text. According to the method, emotional knowledge integration can be well carried out.

Description

technical field [0001] The present invention relates to the technical field of emotion detection and emotion analysis, in particular to a word distributed representation learning system based on emotion knowledge enhancement. Background technique [0002] Sentiment analysis is an important task in natural language processing, which can help consumers, companies and expert systems to make more reasonable decisions. In existing research, word vectors are usually used as research features, and word vectors are used to complete many tasks including sentiment analysis. However, the existing word embedding learning technology does not take into account the target dependence of emotional information when dealing with sentiment analysis. For example: in the comment sentence S1 "The newly purchased computer runs very fast, but its power consumption is also very fast", for the same evaluation "fast", the existing model cannot recognize that for the computer, running "Fast" speed is ...

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 Applications(China)
IPC IPC(8): G06F40/205G06F16/33G06F16/332G06F40/247
CPCG06F40/205G06F40/247G06F16/3329G06F16/3344
Inventor 李优林志舟常亮林煜明
Owner GUILIN UNIV OF ELECTRONIC TECH
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