Natural Language Processing (NLP) based Text Summarization - A Survey
Ishitva Awasthi, Kuntal Gupta, Prabjot Singh Bhogal, Sahejpreet Singh Anand, Piyush Soni
Abstract
The size of data on the Internet has risen in an exponential manner over the past decade. Thus, the need for a solution emerges, that transforms this vast raw information into useful information which a human brain can understand. One such common technique in research that helps in dealing with enormous data is text summarization. Automatic summarization is a renowned approach which is used to reduce a document to its main ideas. It operates by preserving substantial information by creating a shortened version of the text. Text Summarization is categorized into Extractive and Abstractive methods. Extractive methods of summarization minimize the burden of summarization by choosing from the actual text a subset of sentences that are relevant. Although there are a ton of methods, researchers specializing in Natural Language Processing (NLP) are particularly drawn to extractive methods. Based on linguistic and statistical characteristics, the implications of sentences are calculated. A study of extractive and abstract methods for summarizing texts has been made in this paper. This paper also analyses above mentioned methods which yields a less repetitive and a more concentrated summary.