An increasing quantum of data available on the web, news websites, published articles in various fields of study, and electronic books have generated a valuable resource for extracting and analyzing information. The main challenge for researchers has been that of accessing accurate and reliable data. This information must be summarized to retrieve helpful knowledge within a reasonable period. Text summarization is the process of automatically creating a condensed form of documents and preserving its data into a shorter version with overall meaning. Text summarization is divided into Extractive and Abstractive Summarization. The extractive summarizer extracts the basic sentences or phrases from the original document. In contrast, an Abstractive summarizer generates a summary by rephrasing the original text with the new one, which is closed to the human-made. If we consider research for summarization in Indian Language mostly work done of extractive, now researcher move towards the abstractive summarization. Language tools such as Part of Speech taggers and Named Entity Recognizer for Indian languages are not very competitive. Hence, language-specific techniques do not perform very well for Indian languages. With the advent of deep learning architectures, many tasks relating to natural language processing have been achieved; hence can overcome these short comes. This paper reviews existing techniques applied for abstractive text summarization of the Indian regional Language and its significance. In addition, the survey represents the Deep Learning-based abstractive text summarization with valuable adoption of conventional approaches to uplift the abstractive text summarization.