Abstractive Text Summarization Models Using Machine Learning Algorithms

In today's era of cyberspace and intermedia, the number of e-documents have been enlarged enormously. The speedy growth of large data and documents in the field of Data Mining and emerging domain such as Information Retrieval (IR) and the demanding area of Natural Language Processing (NLP) needs Automated Text Summarization. Text Summarization is a process that decreases size of the source document while keeping its important information with actual meaning. It is burdensome and laborious for Homo sapiens to physically do the summarization of huge documents of text. Thus it is necessary to revise old methods and techniques of abstractive text summarization models and modernize them to be efficient and fulfill the requirements of users as per the need by resolving issues of continuously increased data. Now this paper presents a survey of the current futuristic models and the various algorithms and techniques used in Abstractive Text Summarization systems liable to be subjected to an Encoder-Decoder framework. This research can help to gain the overall concepts of recent machine learning algorithms and encoder-decoder architecture resting on abstractive text summarization prototypes with a review of the challenges, issues, and future scope of these models. This research can help solve the research community's problems, newsletters, email overload, and media monitoring.