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

A word vector representation learning method and system based on semantic metalanguage

A word vector and metalanguage technology, applied in semantic analysis, natural language data processing, instruments, etc., can solve problems such as low precision and low usability

Active Publication Date: 2022-03-11
CHINA UNIV OF GEOSCIENCES (WUHAN)
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is to provide a semantic metalanguage-based word vector representation learning method and system to solve the above-mentioned problems

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 word vector representation learning method and system based on semantic metalanguage
  • A word vector representation learning method and system based on semantic metalanguage

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, the specific implementation manners of the present invention will now be described in detail with reference to the accompanying drawings.

[0022] A word vector representation learning method based on semantic metalanguage, such as figure 1 shown, including the following three steps:

[0023] Step 1: Input the preset English dictionary to obtain the semantic metalanguage vocabulary corresponding to all the words in the preset English dictionary;

[0024] Step 2: Obtain the corresponding basic word vector (such as word2vec, etc.) according to the obtained semantic metalanguage vocabulary;

[0025] Step 3: Select the target vocabulary in the preset English dictionary, and obtain the target word vector of the target vocabulary according to the definition of the target vocabulary in the original sentence or paragraph and the basic word vector.

[0026] In the...

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 word vector representation learning method based on semantic metalanguage, comprising the following three steps: inputting a preset English dictionary, obtaining semantic metalanguage vocabulary corresponding to all vocabulary in the preset English dictionary; The corresponding basic word vector is obtained for the vocabulary; the target vocabulary is selected in the preset English dictionary, and the target word vector of the target vocabulary is obtained according to the definition of the target vocabulary in the original sentence or paragraph and the basic word vector. The specific steps to obtain the target word vector of the target vocabulary are: replace the meaning of each word with the original sentence, and retain the meaning of the sentence that is closest to the original sentence, that is, get the accurate definition of the target vocabulary Paraphrase, use the word vector of the corresponding semantic metalanguage vocabulary to accurately paraphrase to properly express the target word, and then the target word vector of the target vocabulary can be obtained.

Description

technical field [0001] The present invention specifically relates to a semantic metalanguage-based word vector representation learning method and system. Background technique [0002] Representation learning is a collection of techniques for learning a feature: converting raw data into a form that can be efficiently exploited by machine learning. It avoids the trouble of manually extracting features, and allows the computer to learn how to extract features while learning to use them. The most intuitive word representation method in the existing representation learning is One-hotRepresentation. This method represents each word as a very long vector. The dimension of this vector is the size of the vocabulary, and most of the elements are 0. Only one dimension has a value of 1, and this dimension represents the current word. In addition to One-hotRepresentation, there are many methods such as word2vec to obtain word vectors, which generally require a "training-test-evaluation...

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): G06F40/284G06F40/30
CPCG06F40/284G06F40/30
Inventor 刘超姚宏李旦董理君康晓军李新川郑坤
Owner CHINA UNIV OF GEOSCIENCES (WUHAN)
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