Comprehensive Survey on Abstractive Text Summarization

Abstract

Over the past few years, we have seen the rise of Automation for the purpose of human convenience. Using ML learning approach, we inch ever closer towards achieving a general purpose AI. The field of Artificial Intelligence (AI) can roughly be divided into three parts namely Machine Learning (ML), Computer Vision and Natural Language Processing (NLP). NLP involves the understanding and handling of human language of which Automatic Text Summarization is an important part. Text summarization is the process of shortening a lengthy document into a short summary. It creates fluent and coherent information while maintaining the context (meaning) of the information. It is a difficult task for human beings to generate a manual summary since it requires a rigorous analysis of the entire document. In order to reduce human efforts and time, automatic summarization techniques prove to be helpful. Text summarization has broadly two techniques, namely Extractive text summarization and abstractive text summarization. Extractive technique relies on extraction of key words, whereas in abstractive text summarization technique utilizes the principles of deep learning to generate the required