Analysis and Implemented on Automated Text Summarization using Transformer Model

Despite the fact that the work on automatic text summarization initially began 70 years prior, it has seen a remarkable development in the recent years due to new and advanced technologies. With the increasing significance of time, the need of condensed and precise information is on peak. No one has time to go through all the articles to get the right data. With the help of automatic text summarizer, we can shorten the source text while maintaining its data and overall meaning, thus saving time of the reader. Text summarization can extensively be alienated into two classifications, Abstractive Summarization also Extractive Summarization. Extractive summarization goals at distinguishing the foremost vital info that is at that moment separated and assembled system to a condensed summary. Abstractive summary group includes rewriting the complete article and the summary is created using natural language processing techniques. In this paper, we have discussed various text summarization models and presented the results of our own implementation of automatic text summarizer which was trained using the CNN Daily mail dataset.