Abstract:

Text Summarization has always been an area of active interest in the academia. In recent times, even though several techniques have being developed for automatic text summarization, efficiency is still a concern. Given the increase in size and number of documents available online, an efficient automatic news summarizer is the need of the hour. In this paper, we propose a technique of text summarization which focuses on the problem of identifying the most important portions of the text and producing coherent summaries. In our methodology, we don’t require full semantic interpretation of the text, instead we create a summary using a model of topic progression in the text derived from lexical chains. It uses the transformers model and compares the Bart model to see which model helps generate the best summaries on average. After passing around 1000 articles of data, we found out that the Bart model outperformed in every aspect albeit the difference was not very large. This tells us that for mid-sized news articles, the Bart Model is better than the other model when it comes to text-summarization.

Keywords: text-summarization, news articles, news summarizer, Bart Model