Scholarlink

<p>Auto Text Summarization (ATS) revolutionized almost every area from business, legal sector, education to medical sector by condensing the text and giving main information about a lengthy document in a quick span of time. The objective of this manuscript is to provide the detailed study of the text summarization from origin to the state of the art. There have been a number of surveys carried out in ATS on many facets. A few surveys focusing on statistical, others on deep learning, extractive, abstractive, hybrid ATS but very few incorporating all these in one. There is a lack of surveys that incorporate detailed Natural Language Processing (NLP) along with ATS. To fulfill these gaps, this study provides a detailed review of ATS techniques and NLP utilization in ATS by considering research papers from 2017 to 2025. This review also provides a multi facets novel comparative analysis based on features (complexity, resources, grammatical precision, cohesiveness and information preservation) and different qualitative and quantitative metrics of extractive, abstractive and hybrid ATS to help the researchers to identify summarization technique as per the need.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Context Based Review on Auto Text Summarization Techniques Using Natural Language Processing for Performing Evaluation and Comparative Analysis of ATS Techniques

  • 期刊论文

  • 发表日期：

    2025年12月18日

查看全文
  • Neeru Sharma,
  • Saravjeet Singh,
  • Monit Kapoor

摘要

Auto Text Summarization (ATS) revolutionized almost every area from business, legal sector, education to medical sector by condensing the text and giving main information about a lengthy document in a quick span of time. The objective of this manuscript is to provide the detailed study of the text summarization from origin to the state of the art. There have been a number of surveys carried out in ATS on many facets. A few surveys focusing on statistical, others on deep learning, extractive, abstractive, hybrid ATS but very few incorporating all these in one. There is a lack of surveys that incorporate detailed Natural Language Processing (NLP) along with ATS. To fulfill these gaps, this study provides a detailed review of ATS techniques and NLP utilization in ATS by considering research papers from 2017 to 2025. This review also provides a multi facets novel comparative analysis based on features (complexity, resources, grammatical precision, cohesiveness and information preservation) and different qualitative and quantitative metrics of extractive, abstractive and hybrid ATS to help the researchers to identify summarization technique as per the need.