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

Embedded representation obtaining and citation recommendation method based on deep learning and link prediction

An embedded representation and deep learning technology, applied in the field of document search, can solve problems such as inability to efficiently and comprehensively obtain recommended citations

Active Publication Date: 2020-01-14
NORTHWESTERN POLYTECHNICAL UNIV
View PDF5 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007]Aiming at the deficiencies in the prior art, the purpose of the present invention is to provide a method for obtaining embedded representation and citation recommendation based on deep learning and link prediction, which solves the problem of There are technical problems that cannot efficiently and comprehensively obtain recommended citations

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
  • Embedded representation obtaining and citation recommendation method based on deep learning and link prediction
  • Embedded representation obtaining and citation recommendation method based on deep learning and link prediction
  • Embedded representation obtaining and citation recommendation method based on deep learning and link prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] This embodiment provides a method for obtaining embedded representations based on deep learning and link prediction, including the following steps:

[0054] Step 1, obtaining the citation network to be represented, the citation network to be represented includes N paper nodes and feature information of each paper node, and N is a positive integer;

[0055] In the present invention, the paper node feature information includes text, tags and collaborative information, etc. The node link information of the citation network can be obtained only by reading and recording the reference part of the paper. Many paper websites directly provide reference lists, such as Google Scholar, Digital Bibliography & Library Project (DBLP), etc., only need to crawl, and after the acquisition is completed, the adjacency matrix or adjacency list between the converted paper nodes is stored.

[0056] Step 2, obtain the embedding representation of each paper node, including:

[0057] Step 21. C...

Embodiment 2

[0104] In this embodiment, a citation recommendation method based on deep learning and link prediction is disclosed, which is used to obtain a recommended sequence for citations to be recommended in the citation network to be recommended, and is performed according to the following steps:

[0105] Step 1, obtain the paper node of the citation to be recommended, and use the method of step 2 in the method for obtaining the embedded representation based on deep learning and link prediction in Embodiment 1 to obtain the embedded representation of the paper node of the citation to be recommended;

[0106] Step II, using the embedding representation acquisition method based on deep learning and link prediction to obtain the embedding representation of each paper node in the citation network to be recommended, and obtain the network embedding representation database;

[0107] Step III. Calculate the cosine similarity between the embedded representation of the paper node to be recommen...

Embodiment 3

[0112] In this embodiment, the citation recommendation method provided by the present invention is compared with the methods in the prior art. In this embodiment, four existing baseline algorithms are selected, as shown in Table 1:

[0113] Table 1 Baseline Algorithms

[0114]

[0115]

[0116] Among them, Doc2Vec is a text embedding algorithm, which only embeds unstructured text information, and DeepWalk and Node2Vec are network embedding algorithms, which only embed structural information. The comparison between the two and the method provided by the present invention can analyze the information provided by the present invention. The method chosen takes advantage of combining structural and unstructural information for embedded representations. On the other hand, TriDNR is an embedded representation algorithm for combining structure and non-structural (text) information designed by predecessors. Compared with the method provided by the present invention, it can reflect...

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 provides a citation recommendation method based on deep learning and link prediction. The citation recommendation method comprises the following steps: step 1, obtaining feature information of all paper nodes in a known paper library and a citation network of the known paper library; step 2, respectively propagating the paper nodes in a citation network to obtain embedded representation of each paper node; step 3, inputting a paper node of a to-be-recommended citation, and calculating embedded representation of the paper node of the to-be-recommended citation; step 4, according to the embedded representation of the paper nodes of the citation to be recommended and the embedded representation of each paper node in the known paper library, recommending the citation to be recommended; and calculating cosine similarities between the paper nodes of the citation to be recommended and each paper node in the known paper library, and selecting the paper nodes corresponding to thefirst t cosine similarities as a citation list of the paper nodes of the citation to be recommended.

Description

technical field [0001] The invention relates to the field of document search, and specifically relates to a method for obtaining embedded representations and citation recommendation based on deep learning and link prediction. Background technique [0002] A scientific research paper needs to cite previous relevant important work to help readers understand its background and innovations. Researchers usually want to quickly understand the existing literature in this field, including which papers are the most relevant, among these papers What are the subtopics etc. Two common ways to find references are: [0003] 1) Search the document on a search engine, such as Google; [0004] 2) Track cited references starting from a small number of initial papers (seed papers). [0005] But the first method is difficult to find a comprehensive keyword list covering all papers, especially for newcomers to a field, and for researchers who specialize in the field, it is also likely to miss...

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): G06F16/335G06F16/338
CPCG06F16/335G06F16/338
Inventor 蔡晓妍顾铭杨黎斌王楠鑫梅欣刘森
Owner NORTHWESTERN POLYTECHNICAL UNIV
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