Recently, there has been an outburst in the amount of text data from various sources, such as the Internet, and archives, such as news articles, scientific papers, and legal documents. Text summarization is an essential tool for analyzing text information.

Automatic text summarization has recently gained more attention in several domains for producing a concise and fluent summary. In real-time applications, artificial intelligence-derived text summarization was exploited. Advanced machine learning and deep learning techniques are explored for single and multi-document text summarization.

Automatic text summarization systems are utilized for various applications such as news summarization, email summarization, legal Summarization, biomedical documents summarization, sentiment summarization, tweet summarization, books, and novel and scientific paper summarization.

Application domains of automatic text summarization are media monitoring, newsletters, search marketing, internal document workflow, financial research, legal contract analysis, social media marketing, biomedical research, question answering and bots, video scripting, books and literature, email overload, e-learning and class assignments, science and research & development, meetings and video-conferencing, help desk and customer support and assisting disabled people.

Several approaches have developed in text summarization, such as extractive method, abstractive method, and multilingual text summarization methods. Some of the impressive concepts in text summarization are:

•  Extractive Summarization: Extractive summarization produces summaries using an intermediate representation, sentence score computation, and summary sentence selection. This summarization approach employs machine learning, deep learning, optimization, and fuzzy logic.

•  Abstractive Summarization: Abstractive Summarization helps to understand the core concept of the document with deep analysis, which applies Template-Based, Rule-Based, Tree-Based, Graph-Based, and deep learning-based methods.

•  Topic Representation: The most broadly utilized topic representation approaches are topic words, frequency-driven approaches, latent semantic analysis, and Bayesian topic models.

•  Knowledge Bases and Automatic Summarization: The advancement of human-generated knowledge bases and various domains has recently gained high scopes in text summarization.

•  Context-Based Summarization: Web Summarization, Scientific Articles Summarization, and Email Summarization are some recently focused context-based text summarization.

•  Indicator Representation: Indicator representation employs graph-based and machine-learning models to determine essential sentences to be included in the sentence summary.