Conceptual Model of Neural Network Algorithmization of Semantic Processing of Scientific and Technical Information

The use of neural network language models to increase the efficiency of processing scientific and technical information (STI) on the Internet from the point of view of cognitive information retrieval is considered. A conceptual model is proposed to identify subject areas that corresponding to the ob...

Full description

Saved in:
Bibliographic Details
Published in:Automatic documentation and mathematical linguistics Vol. 59; no. 2; pp. 78 - 85
Main Authors: Pistsov, S. M., Trusov, V. A.
Format: Journal Article
Language:English
Published: Moscow Pleiades Publishing 01.04.2025
Springer Nature B.V
Subjects:
Algorithms
Classification
Computer Science
Conceptual models
Data mining
Documents
Indexing
Information
Information needs
Information processing
Information retrieval
Information Search
Information Storage and Retrieval
Internet
Internet resources
Knowledge
Language modeling
Language usage
Large language models
Machine learning
Neural networks
Ontology
Retrieval
Search engines
Semantic processing
Semantics
Sexually transmitted diseases
STD
Taxonomy
Technical information
Tracking
cognitive information retrieval
document indexing
information retrieval systems
centroid
neural networks
scientific and technical information
metasearch system
semantic search
language models
ISSN:0005-1055, 1934-8371
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The use of neural network language models to increase the efficiency of processing scientific and technical information (STI) on the Internet from the point of view of cognitive information retrieval is considered. A conceptual model is proposed to identify subject areas that corresponding to the object of information need based on existing STI classification systems. The model is based on the principles of coordinate indexing incorporating methods of detecting and tracking topics and the use of large language models to analyze the information space of the user’s information needs, metasearch of Internet resources, automatic abstracting and ranking of relevant documents.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0005-1055
1934-8371
DOI:10.3103/S0005105525700529