Research Area:  Machine Learning

Abstract:

Text document analysis has recently emerged as a promising strategy in content summarization domain. The analysis can be carried out in two stages: Text abstraction, the process of summarizing a document by including the most critical information from the original document; Text summarization, the process of generalizing redundant information in order to determine the significance of the issue. Automated text summarization is a technique used for extracting the most meaningful information from a document or group of related papers and assembling it into a concise version by retaining the overall meaning of the text document. The text abstraction model is mostly associated with the content extraction process, whereas to perform text summarization, the Natural Language Processing (NLP) technique is used to extract the necessary information from a lengthy text document. To perform efficient and automated text processing and summarization, this research study suggests a novel ensemble topic vector clustering technique, which utilizes Semantic Analysis (SA) to analyze the content. Further, the proposed study concentrates on the process of topic summarizaton to investigate various strategies and perform problem identification. Finally, the proposed study examines the significance of summarization implementation by comparing it with similar existing approaches.

Keywords:  
Topic summarization
Abstraction
Extraction
Content analysis
Semantic analysis
Document modeling
Cluster models

Author(s) Name:   G. Bharathi Mohan, R. Prasanna Kumar

Publisher name:  Elsevier

DOI:  10.1007/978-981-19-5845-8_60

Volume Information:  

Paper Link:   https://link.springer.com/chapter/10.1007/978-981-19-5845-8_60