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

Emotion triple extraction method based on span sharing and grammar dependency relationship enhancement

A technology of dependencies and triples, applied in the field of sentiment analysis

Pending Publication Date: 2021-12-03
GUILIN UNIV OF ELECTRONIC TECH
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this task is quite challenging since it needs to extract aspect terms and opinion terms and the corresponding sentiment expressions

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
  • Emotion triple extraction method based on span sharing and grammar dependency relationship enhancement
  • Emotion triple extraction method based on span sharing and grammar dependency relationship enhancement
  • Emotion triple extraction method based on span sharing and grammar dependency relationship enhancement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] task definition

[0054] Given a sentence S consisting of n words x ={x 1 ,...x i ,...,x n}, the purpose of the aspect-level sentiment triplet extraction task is to extract all sentiment triplets T={(a i ,o i ,s i )|(a i ,o i )∈p∧s i ∈ S}. Among them, p={i ,o i >a i ∈A,o i ∈0} represents a pair of aspect terms and opinion terms (AT, OT), and the expression of its emotional polarity S = (Positive, Neutral, Negative).

[0055] Overall structure

[0056] The overall structure is as figure 2 As shown, it mainly consists of four parts: encoder layer, dependency graph neural network layer, span generation and filtering, and sentiment classifier. In general, given a comment sentence S, we use BERT as our core skeleton to learn the semantics of the context. At the same time, considering the interference between different triples, we need to better capture the relationship between aspect terms and opinion terms, we design a new graph neural network model based o...

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 sentiment analysis, in particular to a sentiment triple extraction method based on span sharing and grammar dependency relationship enhancement, which comprises the following steps of: 1, obtaining feature representation through an encoder layer; 2, enhancing semantic representation through a dependency graph neural network layer; 3, generating spans and filtering out invalid spans; and 4, completing classification through an emotion classifier. According to the invention, the triple can be better extracted.

Description

technical field [0001] The invention relates to the technical field of emotion analysis, in particular to an emotion triplet extraction method based on span sharing and grammatical dependency enhancement. Background technique [0002] Aspect-level sentiment analysis is an important field in natural language processing, and the core objects involved are aspect terms and opinion terms. In commentary sentences, aspect terms are usually attributes or entities being described, and the sentiment expressed by them is usually represented by opinion terms. Currently, most methods solve the aspect-level sentiment analysis task by decomposing it into multiple independent subtasks, such as aspect term extraction (AE), whose goal is to extract all aspect terms in a sentence. Furthermore, opinion term extraction (OE) usually relies on given aspect terms for opinion term extraction. However, these methods need to be combined in a pipelined manner to solve a complete ABSA task, which is p...

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): G06F40/247G06F40/216G06N3/04G06N3/08
CPCG06F16/353G06F40/211G06F40/30G06F40/216G06N3/084G06N3/047G06N3/045Y02D10/00
Inventor 李优林涌东常亮林煜明
Owner GUILIN UNIV OF ELECTRONIC TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com