Method, device and storage medium for semantic similarity matching

A technology of semantic similarity and matching method, applied in the field of semantic similarity matching method, device and storage medium, can solve the problems of tight connection of residual blocks, no semantic information captured, feature loss, etc.

Active Publication Date: 2022-05-13
GUILIN UNIV OF ELECTRONIC TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the RE2 model uses the residual connection to deepen the network depth, the RE2 model residual connection uses the summation method, which does not make the output features of each residual block closely connected with the original features, which is easy to cause feature loss
In addition, for the information interaction between sentences, the attention mechanism is used for word-level interaction, so that the model only learns the similar semantic features between sentence pairs, and does not capture more semantic information of sentence pairs, such as difference semantic features. and key semantic features

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, device and storage medium for semantic similarity matching
  • Method, device and storage medium for semantic similarity matching
  • Method, device and storage medium for semantic similarity matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] like figure 1 As shown, a semantic similarity matching method includes the following steps:

[0072] Importing the first sample to be analyzed and the second sample to be analyzed, respectively performing word vectorization processing on the first sample to be analyzed and the second sample to be analyzed, to obtain the first word corresponding to the first sample to be analyzed a vector matrix and a second word vector matrix corresponding to the second sample to be analyzed;

[0073] Constructing a training network, performing feature fusion processing on the first word vector matrix and the second word vector matrix through the training network, to obtain the first fusion vector matrix corresponding to the first word vector matrix and the corresponding The second fusion vector matrix corresponding to the second word vector matrix;

[0074] performing vector conversion on the first fusion vector matrix and the second fusion vector matrix respectively, to obtain a fir...

Embodiment 2

[0080] A semantic similarity matching method, comprising the steps of:

[0081] Importing the first sample to be analyzed and the second sample to be analyzed, respectively performing word vectorization processing on the first sample to be analyzed and the second sample to be analyzed, to obtain the first word corresponding to the first sample to be analyzed a vector matrix and a second word vector matrix corresponding to the second sample to be analyzed;

[0082] Constructing a training network, performing feature fusion processing on the first word vector matrix and the second word vector matrix through the training network, to obtain the first fusion vector matrix corresponding to the first word vector matrix and the corresponding The second fusion vector matrix corresponding to the second word vector matrix;

[0083] performing vector conversion on the first fusion vector matrix and the second fusion vector matrix respectively, to obtain a first transformation vector matr...

Embodiment 3

[0096] A semantic similarity matching method, comprising the steps of:

[0097] Importing the first sample to be analyzed and the second sample to be analyzed, respectively performing word vectorization processing on the first sample to be analyzed and the second sample to be analyzed, to obtain the first word corresponding to the first sample to be analyzed a vector matrix and a second word vector matrix corresponding to the second sample to be analyzed;

[0098] Constructing a training network, performing feature fusion processing on the first word vector matrix and the second word vector matrix through the training network, to obtain the first fusion vector matrix corresponding to the first word vector matrix and the corresponding The second fusion vector matrix corresponding to the second word vector matrix;

[0099] performing vector conversion on the first fusion vector matrix and the second fusion vector matrix respectively, to obtain a first transformation vector matr...

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 provides a semantic similarity matching method, device and storage medium. The method includes: importing a first sample to be analyzed and a second sample to be analyzed, respectively performing Word vectorization processing to obtain the first word vector matrix corresponding to the first sample to be analyzed and the second word vector matrix corresponding to the second sample to be analyzed; construct a training network, and use the training network to respectively The first word vector matrix and the second word vector matrix are subjected to feature fusion processing to obtain a first fusion vector matrix corresponding to the first word vector matrix and a second fusion vector corresponding to the second word vector matrix matrix. The present invention solves the problems of feature loss, insufficient interaction between sentences, and disappearance of network gradients, enriches the semantic features of sentences, makes the information interaction between sentences more accurate and rich, and can capture more semantic information of sentence pairs.

Description

technical field [0001] The present invention mainly relates to the technical field of language processing, in particular to a semantic similarity matching method, device and storage medium. Background technique [0002] Text matching is an important research field in natural language processing. In the text matching task, the model takes two text sequences as input and predicts the semantic relationship between them. It can be widely used in a variety of tasks, such as natural language reasoning, judging whether a hypothesis can be inferred from a premise, or determining whether two sentences express the same meaning in paraphrase recognition, and answer selection, etc. These applications can Considered as a specific form of the text similarity matching problem, the core problem of text matching is to model the correlation between two sentences. [0003] Nowadays, the most popular method for text matching is deep neural network, and the semantic similarity matching model b...

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): G06F40/30G06F40/284G06F40/194G06K9/62G06N3/04
CPCG06F40/30G06F40/194G06F40/284G06N3/045G06N3/044G06F18/214G06F18/253
Inventor 蔡晓东田文靖
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