Implementing Extractive Summarization Methods on Extractive Datasets

Automatic Text Summarization can be divided into two main approaches: Extractive and Abstractive, depending on how the summary is generated. This research focuses on the experimental analysis of extractive summarization methods using an extractive dataset. In extractive summarization, the key phases include Scoring Sentences and Selecting Sentences. Based on the techniques applied during these phases, extractive summarization can be further classified into several types, such as Frequency-based, Graph-based, Machine Learning-based, Optimization-based, Vector-based, and Transformer-based methods. The current study analyzes these methods using an extractive dataset and evaluates their performance through ROUGE metrics.