Evaluating the Efficacy of Text Summarization Models: A Comparison of NLP Algorithms

Text Summarization is a critical tool nowadays. People do not have enough time to read big articles which take a lot of time. A short summary is no doubt an enthralling option for this case. As this demand increases numerous algorithms and methods have come up which can serve this purpose. This survey paper encompasses the different algorithms and methods used by different researchers which includes methods like TF-IDF and LSA alongside neural networks like Seq2Seq, Pegasus, and Transformer-based models like BART and T5. We analyze these on metrics like ROUGE scores. This survey paper will provide a valuable resource for researchers in the future who want to study text summarization in the news domain.