Revolutionizing Text Summarization: A Comprehensive Comparative Analysis of NLP-Based Models

This research addresses the importance of advancing text summarization by integrating NLP-Based Deep Learning techniques, particularly in abstractive summarization. The primary goal is to enhance automated summarization methods to improve information retention and manage escalating data volumes. The study uses pre-trained machine learning models to generate accurate and coherent summaries aligned with human perception. The problem involves the need for more effective text summarization in the face of increasing data complexity. The methodology employs a comprehensive comparative analysis of models, including Flan T5 and T5-small, using a dataset of 16,000 chat dialogue messages with summaries. Results demonstrate the standout performance of Flan-T5 in capturing unigram, bigram, and long-range dependencies, emphasizing its proficiency in generating summaries closely aligned with reference text. The implications of this work extend to the advancement of abstractive text summarization techniques, contributing to more efficient information extraction and utilization in various domains, particularly in the biomedical field.