Lattice abstraction-based content summarization using baseline abstractive lexical chaining progress

Text summarization is essential in this fast-growing world to read the information because a vast amount of information holds various definitions among related contents. Due to this, reading loads of information documents becomes more tedious. Most text summarization techniques are based on informat...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of information technology (Singapore. Online) Jg. 15; H. 1; S. 369 - 378
Hauptverfasser: Mohan, G. Bharathi, Kumar, R. Prasanna
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Singapore Springer Nature Singapore 01.01.2023
Springer Nature B.V
Schlagworte:
Abstracts
Archives & records
Artificial Intelligence
Chaining
Clusters
Computer Imaging
Computer Science
Content analysis
Data processing
Deep learning
Dictionaries
Documents
Genetic algorithms
Image Processing and Computer Vision
Information retrieval
Keywords
Machine Learning
Natural language processing
Neural networks
Optimization
Original Research
Pattern Recognition and Graphics
Readability
Semantic analysis
Semantics
Sentences
Software Engineering
Text editing
Unstructured data
Vision
Syntactic analysis
Lattice terms
Text abstraction and extraction
Text summarization
Document analysis
ISSN:2511-2104, 2511-2112
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Text summarization is essential in this fast-growing world to read the information because a vast amount of information holds various definitions among related contents. Due to this, reading loads of information documents becomes more tedious. Most text summarization techniques are based on information extraction from unstructured documents, leading to more non-residual abstraction in sentence case analysis. To resolve this problem, a Lattice abstraction-based content summarization (Labs-CS) is proposed to reduce the unstructured documents using the Intra sub-cluster to precipitate sentences. Initially, this proposed method preprocesses natural language processing with a dictionary of terms to make corpus reader content analysis and then de-noises the contents by eliminating the nonstructural text in segmented sentences. Depending on the structural segmentation, the key terms are grouped into clusters and summarized in the sentences into intra-cluster comparisons in another cluster. It creates a lattice-based essential term fragmentation; the text terms are splatted into residual and non-residual terms, then the residual terms are compared with a dictionary of syntactic words which are extracted. Based on the extracted terms, Baseline Abstractive Sentences (BAS) are created using Lexical Chaining Progress (LCP). Finally, the syntactic sequence analyzer combines the extracted term to summarize a document. The proposed system produces high performance by achieving high coherence to reduce the complexity of summarized multilingual documents.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2511-2104
2511-2112
DOI:10.1007/s41870-022-01080-y