<p>A comprehensive and systematic exposition on Automatic Text</p>
<p>Summarization Technique: A deeper coverage on extractive,</p>
<p>abstractive and hybrid methods</p>
<p>Sini Raj Pulari1 , Umadevi Maramreddy1 , Shriram K. Vasudevan2,&lowast;</p>
<p>1Dept. of CSE, Vignan&rsquo;s Foundation for Science, Technology and Research, Guntur, Andhra Pradesh, India</p>
<p>2Intel India Pvt. Ltd., Bengaluru, India</p>
<p>Emails: Emails: sinikishan@gmail.com; umamaramreddy@gmail.com; shriram.kris.vasudevan@intel.com</p>
<p>Abstract</p>
<p>Artificial Intelligence&rsquo;s remarkable advancement and Natural Language Processing enabled innovations that</p>
<p>fulfill various vertical requirements. News summarization has become a popular topic where systems extract</p>
<p>valuable semantic content and generate shorter abstracts from the original content. News readers benefit from a</p>
<p>quick understanding of essential details because an informative summary provides them with important points</p>
<p>without forced reading of the whole article. This article covers essential NLP news summarization methods,</p>
<p>including Abstractive summarization, Extractive summarization, and Hybrid summarization, together with re-</p>
<p>cent datasets, evaluation metrics, applications and future challenges. The main benefit of this work serves both</p>
<p>researchers by providing them with complete information about contemporary summarization developments</p>
<p>to select suitable summarization models during application development.</p>
<p>Keywords: Extractive summarization; Abstractive summarization; Natural Language Processing; News Rec-</p>
<p>ommendations</p>